Adding entity node to core (#6648)

* first draft

* finishing first commit

* adding testing project

* adding changie

* cleaning

* removing blocks

* fixing proto error message

* updates to events

* fixing issues

* adding test dimension

* updating schemas

* updating manfiest.json

* removing old versions from compatability

* updating

* fixes

* fixing more bugs caught by tests

* updating tests

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.4.0a1
+current_version = 1.5.0a1
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)

.changes/0.0.0.md

@@ -3,6 +3,7 @@
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
 * [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
 * [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)
 * [1.1](https://github.com/dbt-labs/dbt-core/blob/1.1.latest/CHANGELOG.md)

.changes/unreleased/Dependency-20221007-000848.yaml

@@ -1,7 +0,0 @@
-kind: "Dependency"
-body: "Bump black from 22.8.0 to 22.10.0"
-time: 2022-10-07T00:08:48.00000Z
-custom:
-  Author: dependabot[bot]
-  Issue: 4904
-  PR: 6019

.changes/unreleased/Docs-20220908-154157.yaml

@@ -1,7 +0,0 @@
-kind: Docs
-body: minor doc correction
-time: 2022-09-08T15:41:57.689162-04:00
-custom:
-  Author: andy-clapson
-  Issue: "5791"
-  PR: "5684"

.changes/unreleased/Docs-20221007-090656.yaml

@@ -1,7 +0,0 @@
-kind: Docs
-body: Generate API docs for new CLI interface
-time: 2022-10-07T09:06:56.446078-05:00
-custom:
-  Author: stu-k
-  Issue: "5528"
-  PR: "6022"

.changes/unreleased/Features-20220912-125935.yaml

@@ -1,7 +0,0 @@
-kind: Features
-body: Friendlier error messages when packages.yml is malformed
-time: 2022-09-12T12:59:35.121188+01:00
-custom:
-  Author: jared-rimmer
-  Issue: "5486"
-  PR: "5812"

.changes/unreleased/Features-20220914-095625.yaml

@@ -1,7 +0,0 @@
-kind: Features
-body: Migrate dbt-utils current_timestamp macros into core + adapters
-time: 2022-09-14T09:56:25.97818-07:00
-custom:
-  Author: colin-rogers-dbt
-  Issue: "5521"
-  PR: "5838"

.changes/unreleased/Features-20221003-110705.yaml

@@ -1,7 +0,0 @@
-kind: Features
-body: extend -f flag shorthand for seed command
-time: 2022-10-03T11:07:05.381632-05:00
-custom:
-  Author: dave-connors-3
-  Issue: "5990"
-  PR: "5991"

.changes/unreleased/Features-20230118-134804.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Adding the entity node
+time: 2023-01-18T13:48:04.487817-06:00
+custom:
+  Author: callum-mcdata
+  Issue: "6627"

.changes/unreleased/Fixes-20220916-104854.yaml

@@ -1,7 +0,0 @@
-kind: Fixes
-body: Account for disabled flags on models in schema files more completely
-time: 2022-09-16T10:48:54.162273-05:00
-custom:
-  Author: emmyoop
-  Issue: "3992"
-  PR: "5868"

.changes/unreleased/Fixes-20221010-113218.yaml

@@ -1,7 +0,0 @@
-kind: Fixes
-body: Add validation of enabled config for metrics, exposures and sources
-time: 2022-10-10T11:32:18.752322-05:00
-custom:
-  Author: emmyoop
-  Issue: "6030"
-  PR: "6038"

.changes/unreleased/Fixes-20221011-160715.yaml

@@ -1,7 +0,0 @@
-kind: Fixes
-body: check length of args of python model function before accessing it
-time: 2022-10-11T16:07:15.464093-04:00
-custom:
-  Author: chamini2
-  Issue: "6041"
-  PR: "6042"

.changes/unreleased/Under the Hood-20220927-194259.yaml

@@ -1,7 +0,0 @@
-kind: Under the Hood
-body: Put black config in explicit config
-time: 2022-09-27T19:42:59.241433-07:00
-custom:
-  Author: max-sixty
-  Issue: "5946"
-  PR: "5947"

.changes/unreleased/Under the Hood-20220929-134406.yaml

@@ -1,7 +0,0 @@
-kind: Under the Hood
-body: Added flat_graph attribute the Manifest class's deepcopy() coverage
-time: 2022-09-29T13:44:06.275941-04:00
-custom:
-  Author: peterallenwebb
-  Issue: "5809"
-  PR: "5975"

.changes/unreleased/Under the Hood-20221005-120310.yaml

@@ -1,7 +0,0 @@
-kind: Under the Hood
-body: Add mypy configs so `mypy` passes from CLI
-time: 2022-10-05T12:03:10.061263-07:00
-custom:
-  Author: max-sixty
-  Issue: "5983"
-  PR: "5983"

.changes/unreleased/Under the Hood-20221007-094627.yaml

@@ -1,7 +0,0 @@
-kind: Under the Hood
-body: Exception message cleanup.
-time: 2022-10-07T09:46:27.682872-05:00
-custom:
-  Author: emmyoop
-  Issue: "6023"
-  PR: "6024"

.changes/unreleased/Under the Hood-20221007-140044.yaml

@@ -1,7 +0,0 @@
-kind: Under the Hood
-body: Add dmypy cache to gitignore
-time: 2022-10-07T14:00:44.227644-07:00
-custom:
-  Author: max-sixty
-  Issue: "6028"
-  PR: "5978"

.changes/unreleased/Under the Hood-20230113-132513.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Fix use of ConnectionReused logging event
+time: 2023-01-13T13:25:13.023168-05:00
+custom:
+  Author: gshank
+  Issue: "6168"

.changes/unreleased/Under the Hood-20230117-111737.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Update deprecated github action command
+time: 2023-01-17T11:17:37.046095-06:00
+custom:
+  Author: davidbloss
+  Issue: "6153"

.changie.yaml

@@ -6,19 +6,67 @@ changelogPath: CHANGELOG.md
 versionExt: md
 versionFormat: '## dbt-core {{.Version}} - {{.Time.Format "January 02, 2006"}}'
 kindFormat: '### {{.Kind}}'
-changeFormat: '- {{.Body}} ([#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), [#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+changeFormat: |-
+  {{- $IssueList := list }}
+  {{- $changes := splitList " " $.Custom.Issue }}
+  {{- range $issueNbr := $changes }}
+    {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $issueNbr }}
+    {{- $IssueList = append $IssueList $changeLink  }}
+  {{- end -}}
+  - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
 
 kinds:
   - label: Breaking Changes
   - label: Features
   - label: Fixes
   - label: Docs
-    changeFormat: '- {{.Body}} ([dbt-docs/#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-docs/issues/{{.Custom.Issue}}), [dbt-docs/#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-docs/pull/{{.Custom.PR}}))'
+    changeFormat: |-
+      {{- $IssueList := list }}
+      {{- $changes := splitList " " $.Custom.Issue }}
+      {{- range $issueNbr := $changes }}
+        {{- $changeLink := "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $issueNbr }}
+        {{- $IssueList = append $IssueList $changeLink }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $IssueList }}{{if $index}}, {{end}}{{$element}}{{end}})
   - label: Under the Hood
   - label: Dependencies
-    changeFormat: '- {{.Body}} ({{if ne .Custom.Issue ""}}[#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), {{end}}[#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
   - label: Security
-    changeFormat: '- {{.Body}} ({{if ne .Custom.Issue ""}}[#{{.Custom.Issue}}](https://github.com/dbt-labs/dbt-core/issues/{{.Custom.Issue}}), {{end}}[#{{.Custom.PR}}](https://github.com/dbt-labs/dbt-core/pull/{{.Custom.PR}}))'
+    changeFormat: |-
+      {{- $PRList := list }}
+      {{- $changes := splitList " " $.Custom.PR }}
+      {{- range $pullrequest := $changes }}
+        {{- $changeLink := "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $pullrequest }}
+        {{- $PRList = append $PRList $changeLink  }}
+      {{- end -}}
+      - {{.Body}} ({{ range $index, $element := $PRList }}{{if $index}}, {{end}}{{$element}}{{end}})
+    skipGlobalChoices: true
+    additionalChoices:
+      - key: Author
+        label: GitHub Username(s) (separated by a single space if multiple)
+        type: string
+        minLength: 3
+      - key: PR
+        label: GitHub Pull Request Number (separated by a single space if multiple)
+        type: string
+        minLength: 1
 
 newlines:
   afterChangelogHeader: 1
@@ -33,42 +81,41 @@ custom:
   type: string
   minLength: 3
 - key: Issue
-  label: GitHub Issue Number
+  label: GitHub Issue Number (separated by a single space if multiple)
-  type: int
+  type: string
-  minInt: 1
+  minLength: 1
-- key: PR
-  label: GitHub Pull Request Number
-  type: int
-  minInt: 1
 
 footerFormat: |
   {{- $contributorDict := dict }}
   {{- /* any names added to this list should be all lowercase for later matching purposes */}}
-  {{- $core_team := list "peterallenwebb" "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "dependabot[bot]" "snyk-bot" "colin-rogers-dbt" }}
+  {{- $core_team := list "michelleark" "peterallenwebb" "emmyoop" "nathaniel-may" "gshank" "leahwicz" "chenyulinx" "stu-k" "iknox-fa" "versusfacit" "mcknight-42" "jtcohen6" "aranke" "dependabot[bot]" "snyk-bot" "colin-rogers-dbt" }}
   {{- range $change := .Changes }}
     {{- $authorList := splitList " " $change.Custom.Author }}
-    {{- /* loop through all authors for a PR */}}
+    {{- /* loop through all authors for a single changelog */}}
     {{- range $author := $authorList }}
       {{- $authorLower := lower $author }}
       {{- /* we only want to include non-core team contributors */}}
       {{- if not (has $authorLower $core_team)}}
-        {{- /* Docs kind link back to dbt-docs instead of dbt-core PRs */}}
+        {{- $changeList := splitList " " $change.Custom.Author }}
-        {{- $prLink := $change.Kind }}
+          {{- /* Docs kind link back to dbt-docs instead of dbt-core issues */}}
-        {{- if eq $change.Kind "Docs" }}
+          {{- $changeLink := $change.Kind }}
-          {{- $prLink = "[dbt-docs/#pr](https://github.com/dbt-labs/dbt-docs/pull/pr)" | replace "pr" $change.Custom.PR }}
+          {{- if or (eq $change.Kind "Dependencies") (eq $change.Kind "Security") }}
-        {{- else }}
+            {{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/pull/nbr)" | replace "nbr" $change.Custom.PR }}
-          {{- $prLink = "[#pr](https://github.com/dbt-labs/dbt-core/pull/pr)" | replace "pr" $change.Custom.PR }}
+          {{- else if eq $change.Kind "Docs"}}
-        {{- end }}
+            {{- $changeLink = "[dbt-docs/#nbr](https://github.com/dbt-labs/dbt-docs/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
-        {{- /* check if this contributor has other PRs associated with them already */}}
+          {{- else }}
-        {{- if hasKey $contributorDict $author }}
+            {{- $changeLink = "[#nbr](https://github.com/dbt-labs/dbt-core/issues/nbr)" | replace "nbr" $change.Custom.Issue }}
-          {{- $prList := get $contributorDict $author }}
+          {{- end }}
-          {{- $prList = append $prList $prLink  }}
+          {{- /* check if this contributor has other changes associated with them already */}}
-          {{- $contributorDict := set $contributorDict $author $prList }}
+          {{- if hasKey $contributorDict $author }}
-        {{- else }}
+            {{- $contributionList := get $contributorDict $author }}
-          {{- $prList := list $prLink }}
+            {{- $contributionList = append $contributionList $changeLink  }}
-          {{- $contributorDict := set $contributorDict $author $prList }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
-        {{- end }}
+          {{- else }}
-      {{- end}}
+            {{- $contributionList := list $changeLink }}
+            {{- $contributorDict := set $contributorDict $author $contributionList }}
+          {{- end }}
+        {{- end}}
     {{- end}}
   {{- end }}
   {{- /* no indentation here for formatting so the final markdown doesn't have unneeded indentations */}}

.flake8

@@ -9,4 +9,4 @@ ignore =
     E203 # makes Flake8 work like black
     E741
     E501 # long line checking is done in black
-exclude = test
+exclude = test/

.gitattributes

@@ -0,0 +1,2 @@
+core/dbt/include/index.html binary
+tests/functional/artifacts/data/state/*/manifest.json binary

.github/_README.md

@@ -63,12 +63,12 @@ permissions:
   contents: read
   pull-requests: write
 ```
-    
+
 ### Secrets
 - When to use a [Personal Access Token (PAT)](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token) vs the [GITHUB_TOKEN](https://docs.github.com/en/actions/security-guides/automatic-token-authentication) generated for the action?
 
     The `GITHUB_TOKEN` is used by default.  In most cases it is sufficient for what you need.
-    
+
     If you expect the workflow to result in a commit to that should retrigger workflows, you will need to use a Personal Access Token for the bot to commit the file. When using the GITHUB_TOKEN, the resulting commit will not trigger another GitHub Actions Workflow run. This is due to limitations set by GitHub. See [the docs](https://docs.github.com/en/actions/security-guides/automatic-token-authentication#using-the-github_token-in-a-workflow) for a more detailed explanation.
 
     For example, we must use a PAT in our workflow to commit a new changelog yaml file for bot PRs.  Once the file has been committed to the branch, it should retrigger the check to validate that a changelog exists on the PR.  Otherwise, it would stay in a failed state since the check would never retrigger.
@@ -105,7 +105,7 @@ Some triggers of note that we use:
 
   ```
   # **what?**
-  # Describe what the action does.  
+  # Describe what the action does.
 
   # **why?**
   # Why does this action exist?
@@ -138,7 +138,7 @@ Some triggers of note that we use:
         id: fp
         run: |
           FILEPATH=.changes/unreleased/Dependencies-${{ steps.filename_time.outputs.time }}.yaml
-          echo "::set-output name=FILEPATH::$FILEPATH"
+          echo "FILEPATH=$FILEPATH" >> $GITHUB_OUTPUT
   ```
 
 - Print out all variables you will reference as the first step of a job.  This allows for easier debugging.  The first job should log all inputs.  Subsequent jobs should reference outputs of other jobs, if present.
@@ -158,14 +158,14 @@ Some triggers of note that we use:
         echo "The build_script_path:              ${{ inputs.build_script_path }}"
         echo "The s3_bucket_name:                 ${{ inputs.s3_bucket_name }}"
         echo "The package_test_command:           ${{ inputs.package_test_command }}"
-      
+
     # collect all the variables that need to be used in subsequent jobs
     - name: Set Variables
       id: variables
       run: |
-        echo "::set-output name=important_path::'performance/runner/Cargo.toml'"
+        echo "important_path='performance/runner/Cargo.toml'" >> $GITHUB_OUTPUT
-        echo "::set-output name=release_id::${{github.event.inputs.release_id}}"
+        echo "release_id=${{github.event.inputs.release_id}}" >> $GITHUB_OUTPUT
-        echo "::set-output name=open_prs::${{github.event.inputs.open_prs}}"
+        echo "open_prs=${{github.event.inputs.open_prs}}" >> $GITHUB_OUTPUT
 
   job2:
     needs: [job1]
@@ -190,7 +190,7 @@ ___
 ### Actions from the Marketplace
 - Don’t use external actions for things that can easily be accomplished manually.
 - Always read through what an external action does before using it!  Often an action in the GitHub Actions Marketplace can be replaced with a few lines in bash.  This is much more maintainable (and won’t change under us) and clear as to what’s actually happening.  It also prevents any
-- Pin actions _we don't control_ to tags. 
+- Pin actions _we don't control_ to tags.
 
 ### Connecting to AWS
 - Authenticate with the aws managed workflow
@@ -208,7 +208,7 @@ ___
 
   ```yaml
   - name: Copy Artifacts from S3 via CLI
-    run: aws s3 cp ${{ env.s3_bucket }} . --recursive 
+    run: aws s3 cp ${{ env.s3_bucket }} . --recursive
   ```
 
 ### Testing

.github/actions/latest-wrangler/main.py

@@ -28,11 +28,12 @@ if __name__ == "__main__":
     if package_request.status_code == 404:
         if halt_on_missing:
             sys.exit(1)
-        else:
+        # everything is the latest if the package doesn't exist
-            # everything is the latest if the package doesn't exist
+        github_output = os.environ.get("GITHUB_OUTPUT")
-            print(f"::set-output name=latest::{True}")
+        with open(github_output, "at", encoding="utf-8") as gh_output:
-            print(f"::set-output name=minor_latest::{True}")
+            gh_output.write("latest=True")
-            sys.exit(0)
+            gh_output.write("minor_latest=True")
+        sys.exit(0)
 
     # TODO: verify package meta is "correct"
     # https://github.com/dbt-labs/dbt-core/issues/4640
@@ -91,5 +92,7 @@ if __name__ == "__main__":
     latest = is_latest(pre_rel, new_version, current_latest)
     minor_latest = is_latest(pre_rel, new_version, current_minor_latest)
 
-    print(f"::set-output name=latest::{latest}")
+    github_output = os.environ.get("GITHUB_OUTPUT")
-    print(f"::set-output name=minor_latest::{minor_latest}")
+    with open(github_output, "at", encoding="utf-8") as gh_output:
+        gh_output.write(f"latest={latest}")
+        gh_output.write(f"minor_latest={minor_latest}")

.github/workflows/bot-changelog.yml

@@ -40,7 +40,7 @@ jobs:
       matrix:
         include:
           - label: "dependencies"
-            changie_kind: "Dependency"
+            changie_kind: "Dependencies"
           - label: "snyk"
             changie_kind: "Security"
     runs-on: ubuntu-latest
@@ -58,4 +58,4 @@ jobs:
         commit_message: "Add automated changelog yaml from template for bot PR"
         changie_kind: ${{ matrix.changie_kind }}
         label: ${{ matrix.label }}
-        custom_changelog_string: "custom:\n  Author: ${{ github.event.pull_request.user.login }}\n  Issue: 4904\n  PR: ${{ github.event.pull_request.number }}"
+        custom_changelog_string: "custom:\n  Author: ${{ github.event.pull_request.user.login }}\n  PR: ${{ github.event.pull_request.number }}"

.github/workflows/generate-cli-api-docs.yml

@@ -0,0 +1,165 @@
+# **what?**
+# On push, if anything in core/dbt/docs or core/dbt/cli has been
+# created or modified, regenerate the CLI API docs using sphinx.
+
+# **why?**
+# We watch for changes in core/dbt/cli because the CLI API docs rely on click
+# and all supporting flags/params to be generated. We watch for changes in
+# core/dbt/docs since any changes to sphinx configuration or any of the
+# .rst files there could result in a differently build final index.html file.
+
+# **when?**
+# Whenever a change has been pushed to a branch, and only if there is a diff
+# between the PR branch and main's core/dbt/cli and or core/dbt/docs dirs.
+
+# TODO: add bot comment to PR informing contributor that the docs have been committed
+# TODO: figure out why github action triggered pushes cause github to fail to report
+#       the status of jobs
+
+name: Generate CLI API docs
+
+on:
+  pull_request:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+env:
+  CLI_DIR: ${{ github.workspace }}/core/dbt/cli
+  DOCS_DIR: ${{ github.workspace }}/core/dbt/docs
+  DOCS_BUILD_DIR: ${{ github.workspace }}/core/dbt/docs/build
+
+jobs:
+  check_gen:
+    name: check if generation needed
+    runs-on: ubuntu-latest
+    if: ${{ github.event.pull_request.head.repo.fork == false }}
+    outputs:
+      cli_dir_changed: ${{ steps.check_cli.outputs.cli_dir_changed }}
+      docs_dir_changed: ${{ steps.check_docs.outputs.docs_dir_changed }}
+
+    steps:
+    - name: "[DEBUG] print variables"
+      run: |
+        echo "env.CLI_DIR:        ${{ env.CLI_DIR }}"
+        echo "env.DOCS_BUILD_DIR: ${{ env.DOCS_BUILD_DIR }}"
+        echo "env.DOCS_DIR:       ${{ env.DOCS_DIR }}"
+
+    - name: git checkout
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 0
+        ref: ${{ github.head_ref }}
+
+    - name: set shas
+      id: set_shas
+      run: |
+        THIS_SHA=$(git rev-parse @)
+        LAST_SHA=$(git rev-parse @~1)
+
+        echo "this sha: $THIS_SHA"
+        echo "last sha: $LAST_SHA"
+
+        echo "this_sha=$THIS_SHA" >> $GITHUB_OUTPUT
+        echo "last_sha=$LAST_SHA" >> $GITHUB_OUTPUT
+
+    - name: check for changes in core/dbt/cli
+      id: check_cli
+      run: |
+        CLI_DIR_CHANGES=$(git diff \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.CLI_DIR }})
+
+        if [ -n "$CLI_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $CLI_DIR_CHANGES
+          echo "cli_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "cli_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+    - name: check for changes in core/dbt/docs
+      id: check_docs
+      if: steps.check_cli.outputs.cli_dir_changed == 'false'
+      run: |
+        DOCS_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_DIR }} ':!${{ env.DOCS_BUILD_DIR }}')
+
+        DOCS_BUILD_DIR_CHANGES=$(git diff --name-only \
+          ${{ steps.set_shas.outputs.last_sha }} \
+          ${{ steps.set_shas.outputs.this_sha }} \
+          -- ${{ env.DOCS_BUILD_DIR }})
+
+        if [ -n "$DOCS_DIR_CHANGES" ] && [ -z "$DOCS_BUILD_DIR_CHANGES" ]; then
+          echo "changes found"
+          echo $DOCS_DIR_CHANGES
+          echo "docs_dir_changed=true" >> $GITHUB_OUTPUT
+          exit 0
+        fi
+        echo "docs_dir_changed=false" >> $GITHUB_OUTPUT
+        echo "no changes found"
+
+  gen_docs:
+    name: generate docs
+    runs-on: ubuntu-latest
+    needs: [check_gen]
+    if: |
+      needs.check_gen.outputs.cli_dir_changed == 'true'
+      || needs.check_gen.outputs.docs_dir_changed == 'true'
+
+    steps:
+      - name: "[DEBUG] print variables"
+        run: |
+          echo "env.DOCS_DIR:    ${{ env.DOCS_DIR }}"
+          echo "github head_ref: ${{ github.head_ref }}"
+
+      - name: git checkout
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: install python
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: 3.8
+
+      - name: install dev requirements
+        run: |
+          python3 -m venv env
+          source env/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt -r dev-requirements.txt
+
+      - name: generate docs
+        run: |
+          source env/bin/activate
+          cd ${{ env.DOCS_DIR }}
+
+          echo "cleaning existing docs"
+          make clean
+
+          echo "creating docs"
+          make html
+
+      - name: debug
+        run: |
+          echo ">>>>> status"
+          git status
+          echo ">>>>> remotes"
+          git remote -v
+          echo ">>>>> branch"
+          git branch -v
+          echo ">>>>> log"
+          git log --pretty=oneline | head -5
+
+      - name: commit docs
+        run: |
+          git config user.name 'Github Build Bot'
+          git config user.email 'buildbot@fishtownanalytics.com'
+          git commit -am "Add generated CLI API docs"
+          git push -u origin ${{ github.head_ref }}

.github/workflows/main.yml

@@ -45,7 +45,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
+        with:
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |
@@ -71,7 +73,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     env:
       TOXENV: "unit"
@@ -82,7 +84,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -99,7 +101,9 @@ jobs:
       - name: Get current date
         if: always()
         id: date
-        run: echo "::set-output name=date::$(date +'%Y-%m-%dT%H_%M_%S')" #no colons allowed for artifacts
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
 
       - uses: actions/upload-artifact@v2
         if: always()
@@ -116,8 +120,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
-        os: [ubuntu-latest]
+        os: [ubuntu-20.04]
         include:
           - python-version: 3.8
             os: windows-latest
@@ -137,7 +141,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -166,7 +170,9 @@ jobs:
       - name: Get current date
         if: always()
         id: date
-        run: echo "::set-output name=date::$(date +'%Y_%m_%dT%H_%M_%S')" #no colons allowed for artifacts
+        run: |
+          CURRENT_DATE=$(date +'%Y-%m-%dT%H_%M_%S') # no colons allowed for artifacts
+          echo "date=$CURRENT_DATE" >> $GITHUB_OUTPUT
 
       - uses: actions/upload-artifact@v2
         if: always()
@@ -190,9 +196,9 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4.3.0
         with:
-          python-version: 3.8
+          python-version: '3.8'
 
       - name: Install python dependencies
         run: |

.github/workflows/release-docker.yml

@@ -41,9 +41,9 @@ jobs:
         id: version
         run: |
           IFS="." read -r MAJOR MINOR PATCH <<< ${{ github.event.inputs.version_number }}
-          echo "::set-output name=major::$MAJOR"
+          echo "major=$MAJOR" >> $GITHUB_OUTPUT
-          echo "::set-output name=minor::$MINOR"
+          echo "minor=$MINOR" >> $GITHUB_OUTPUT
-          echo "::set-output name=patch::$PATCH"
+          echo "patch=$PATCH" >> $GITHUB_OUTPUT
 
       - name: Is pkg 'latest'
         id: latest
@@ -70,8 +70,10 @@ jobs:
       - name: Get docker build arg
         id: build_arg
         run: |
-          echo "::set-output name=build_arg_name::"$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
+          BUILD_ARG_NAME=$(echo ${{ github.event.inputs.package }} | sed 's/\-/_/g')
-          echo "::set-output name=build_arg_value::"$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          BUILD_ARG_VALUE=$(echo ${{ github.event.inputs.package }} | sed 's/postgres/core/g')
+          echo "build_arg_name=$BUILD_ARG_NAME" >> $GITHUB_OUTPUT
+          echo "build_arg_value=$BUILD_ARG_VALUE" >> $GITHUB_OUTPUT
 
       - name: Log in to the GHCR
         uses: docker/login-action@v1

.github/workflows/release.yml

@@ -165,7 +165,7 @@ jobs:
         env:
           IS_PRERELEASE: ${{ contains(github.event.inputs.version_number, 'rc') ||  contains(github.event.inputs.version_number, 'b') }}
         run: |
-          echo ::set-output name=isPrerelease::$IS_PRERELEASE
+          echo "isPrerelease=$IS_PRERELEASE" >> $GITHUB_OUTPUT
 
       - name: Creating GitHub Release
         uses: softprops/action-gh-release@v1

.github/workflows/stale.yml

@@ -9,13 +9,4 @@ permissions:
 
 jobs:
   stale:
-    runs-on: ubuntu-latest
+    uses: dbt-labs/actions/.github/workflows/stale-bot-matrix.yml@main
-    steps:
-      # pinned at v4 (https://github.com/actions/stale/releases/tag/v4.0.0)
-      - uses: actions/stale@cdf15f641adb27a71842045a94023bef6945e3aa
-        with:
-          stale-issue-message: "This issue has been marked as Stale because it has been open for 180 days with no activity. If you would like the issue to remain open, please remove the stale label or comment on the issue, or it will be closed in 7 days."
-          stale-pr-message: "This PR has been marked as Stale because it has been open for 180 days with no activity. If you would like the PR to remain open, please remove the stale label or comment on the PR, or it will be closed in 7 days."
-          close-issue-message: "Although we are closing this issue as stale, it's not gone forever. Issues can be reopened if there is renewed community interest; add a comment to notify the maintainers."
-          # mark issues/PRs stale when they haven't seen activity in 180 days
-          days-before-stale: 180

.github/workflows/structured-logging-schema-check.yml

@@ -22,7 +22,7 @@ jobs:
   # run the performance measurements on the current or default branch
   test-schema:
     name: Test Log Schema
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     env:
       # turns warnings into errors
       RUSTFLAGS: "-D warnings"
@@ -46,12 +46,6 @@ jobs:
         with:
           python-version: "3.8"
 
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-
       - name: Install python dependencies
         run: |
           pip install --user --upgrade pip
@@ -69,10 +63,3 @@ jobs:
       # we actually care if these pass, because the normal test run doesn't usually include many json log outputs
       - name: Run integration tests
         run: tox -e integration -- -nauto
-
-      # apply our schema tests to every log event from the previous step
-      # skips any output that isn't valid json
-      - uses: actions-rs/cargo@v1
-        with:
-          command: run
-          args: --manifest-path test/interop/log_parsing/Cargo.toml

.github/workflows/version-bump.yml

@@ -65,7 +65,7 @@ jobs:
       - name: Set branch value
         id: variables
         run: |
-          echo "::set-output name=BRANCH_NAME::prep-release/${{ github.event.inputs.version_number }}_$GITHUB_RUN_ID"
+          echo "BRANCH_NAME=prep-release/${{ github.event.inputs.version_number }}_$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
 
       - name: Create PR branch
         run: |

.gitignore

@@ -11,6 +11,7 @@ __pycache__/
 env*/
 dbt_env/
 build/
+!core/dbt/docs/build
 develop-eggs/
 dist/
 downloads/

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # Eventually the hooks described here will be run as tests before merging each PR.
 
 # TODO: remove global exclusion of tests when testing overhaul is complete
-exclude: ^test/
+exclude: ^(test/|core/dbt/docs/build/)
 
 # Force all unspecified python hooks to run python 3.8
 default_language_version:
@@ -30,7 +30,7 @@ repos:
     args:
     - "--check"
     - "--diff"
-- repo: https://gitlab.com/pycqa/flake8
+- repo: https://github.com/pycqa/flake8
   rev: 4.0.1
   hooks:
   - id: flake8

CHANGELOG.md

@@ -5,12 +5,12 @@
 - "Breaking changes" listed under a version may require action from end users or external maintainers when upgrading to that version.
 - Do not edit this file directly. This file is auto-generated using [changie](https://github.com/miniscruff/changie). For details on how to document a change, see [the contributing guide](https://github.com/dbt-labs/dbt-core/blob/main/CONTRIBUTING.md#adding-changelog-entry)
 
-
 ## Previous Releases
 
 For information on prior major and minor releases, see their changelogs:
 
 
+* [1.4](https://github.com/dbt-labs/dbt-core/blob/1.4.latest/CHANGELOG.md)
 * [1.3](https://github.com/dbt-labs/dbt-core/blob/1.3.latest/CHANGELOG.md)
 * [1.2](https://github.com/dbt-labs/dbt-core/blob/1.2.latest/CHANGELOG.md)
 * [1.1](https://github.com/dbt-labs/dbt-core/blob/1.1.latest/CHANGELOG.md)

CONTRIBUTING.md

@@ -56,7 +56,7 @@ There are some tools that will be helpful to you in developing locally. While th
 
 These are the tools used in `dbt-core` development and testing:
 
-- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, and 3.10
+- [`tox`](https://tox.readthedocs.io/en/latest/) to manage virtualenvs across python versions. We currently target the latest patch releases for Python 3.7, 3.8, 3.9, 3.10 and 3.11
 - [`pytest`](https://docs.pytest.org/en/latest/) to define, discover, and run tests
 - [`flake8`](https://flake8.pycqa.org/en/latest/) for code linting
 - [`black`](https://github.com/psf/black) for code formatting
@@ -96,12 +96,15 @@ brew install postgresql
 
 ### Installation
 
-First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies) with:
+First make sure that you set up your `virtualenv` as described in [Setting up an environment](#setting-up-an-environment).  Also ensure you have the latest version of pip installed with `pip install --upgrade pip`. Next, install `dbt-core` (and its dependencies):
 
 ```sh
 make dev
-# or
+```
+or, alternatively:
+```sh
 pip install -r dev-requirements.txt -r editable-requirements.txt
+pre-commit install
 ```
 
 When installed in this way, any changes you make to your local copy of the source code will be reflected immediately in your next `dbt` run.
@@ -160,7 +163,7 @@ suites.
 
 #### `tox`
 
-[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, and Python 3.10 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
+[`tox`](https://tox.readthedocs.io/en/latest/) takes care of managing virtualenvs and install dependencies in order to run tests. You can also run tests in parallel, for example, you can run unit tests for Python 3.7, Python 3.8, Python 3.9, Python 3.10 and Python 3.11 checks in parallel with `tox -p`. Also, you can run unit tests for specific python versions with `tox -e py37`. The configuration for these tests in located in `tox.ini`.
 
 #### `pytest`
 
@@ -201,13 +204,21 @@ Here are some general rules for adding tests:
 * Sometimes flake8 complains about lines that are actually fine, in which case you can put a comment on the line such as: # noqa or # noqa: ANNN, where ANNN is the error code that flake8 issues.
 * To collect output for `CProfile`, run dbt with the `-r` option and the name of an output file, i.e. `dbt -r dbt.cprof run`. If you just want to profile parsing, you can do: `dbt -r dbt.cprof parse`. `pip` install `snakeviz` to view the output. Run `snakeviz dbt.cprof` and output will be rendered in a browser window.
 
-## Adding a CHANGELOG Entry
+## Adding or modifying a CHANGELOG Entry
 
 We use [changie](https://changie.dev) to generate `CHANGELOG` entries. **Note:** Do not edit the `CHANGELOG.md` directly. Your modifications will be lost.
 
 Follow the steps to [install `changie`](https://changie.dev/guide/installation/) for your system.
 
-Once changie is installed and your PR is created, simply run `changie new` and changie will walk you through the process of creating a changelog entry.  Commit the file that's created and your changelog entry is complete!
+Once changie is installed and your PR is created for a new feature, simply run the following command and changie will walk you through the process of creating a changelog entry:
+
+```shell
+changie new
+```
+
+Commit the file that's created and your changelog entry is complete!
+
+If you are contributing to a feature already in progress, you will modify the changie yaml file in dbt/.changes/unreleased/ related to your change. If you need help finding this file, please ask within the discussion for the pull request!
 
 You don't need to worry about which `dbt-core` version your change will go into. Just create the changelog entry with `changie`, and open your PR against the `main` branch. All merged changes will be included in the next minor version of `dbt-core`. The Core maintainers _may_ choose to "backport" specific changes in order to patch older minor versions. In that case, a maintainer will take care of that backport after merging your PR, before releasing the new version of `dbt-core`.
 

Dockerfile.test

@@ -49,6 +49,9 @@ RUN apt-get update \
     python3.10 \
     python3.10-dev \
     python3.10-venv \
+    python3.11 \
+    python3.11-dev \
+    python3.11-venv \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 

Makefile

@@ -19,11 +19,16 @@ CI_FLAGS =\
 	LOG_DIR=./logs\
 	DBT_LOG_FORMAT=json
 
-.PHONY: dev
+.PHONY: dev_req
-dev: ## Installs dbt-* packages in develop mode along with development dependencies.
+dev_req: ## Installs dbt-* packages in develop mode along with only development dependencies.
 	@\
 	pip install -r dev-requirements.txt -r editable-requirements.txt
 
+.PHONY: dev
+dev: dev_req ## Installs dbt-* packages in develop mode along with development dependencies and pre-commit.
+	@\
+	pre-commit install
+
 .PHONY: mypy
 mypy: .env ## Runs mypy against staged changes for static type checking.
 	@\

core/dbt/README.md

@@ -2,50 +2,59 @@
 
 ## The following are individual files in this directory.
 
-### deprecations.py
-
-### flags.py
-
-### main.py
-
-### tracking.py
-
-### version.py
-
-### lib.py
-
-### node_types.py
-
-### helper_types.py
-
-### links.py
-
-### semver.py
-
-### ui.py
-
 ### compilation.py
 
+### constants.py
+
 ### dataclass_schema.py
 
+### deprecations.py
+
 ### exceptions.py
 
+### flags.py
+
+### helper_types.py
+
 ### hooks.py
 
+### lib.py
+
+### links.py
+
 ### logger.py
 
+### main.py
+
+### node_types.py
+
 ### profiler.py
 
+### selected_resources.py
+
+### semver.py
+
+### tracking.py
+
+### ui.py
+
 ### utils.py
 
+### version.py
+
 
 ## The subdirectories will be documented in a README in the subdirectory
-* config
-* include
 * adapters
-* context
+* cli
-* deps
-* graph
-* task
 * clients
+* config
+* context
+* contracts
+* deps
+* docs
 * events
+* graph
+* include
+* parser
+* task
+* tests

core/dbt/adapters/base/column.py

@@ -2,7 +2,7 @@ from dataclasses import dataclass
 import re
 from typing import Dict, ClassVar, Any, Optional
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 @dataclass
@@ -85,7 +85,7 @@ class Column:
 
     def string_size(self) -> int:
         if not self.is_string():
-            raise RuntimeException("Called string_size() on non-string field!")
+            raise DbtRuntimeError("Called string_size() on non-string field!")
 
         if self.dtype == "text" or self.char_size is None:
             # char_size should never be None. Handle it reasonably just in case
@@ -124,7 +124,7 @@ class Column:
     def from_description(cls, name: str, raw_data_type: str) -> "Column":
         match = re.match(r"([^(]+)(\([^)]+\))?", raw_data_type)
         if match is None:
-            raise RuntimeException(f'Could not interpret data type "{raw_data_type}"')
+            raise DbtRuntimeError(f'Could not interpret data type "{raw_data_type}"')
         data_type, size_info = match.groups()
         char_size = None
         numeric_precision = None
@@ -137,7 +137,7 @@ class Column:
                 try:
                     char_size = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
@@ -145,14 +145,14 @@ class Column:
                 try:
                     numeric_precision = int(parts[0])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[0]}" to an integer'
                     )
                 try:
                     numeric_scale = int(parts[1])
                 except ValueError:
-                    raise RuntimeException(
+                    raise DbtRuntimeError(
                         f'Could not interpret data_type "{raw_data_type}": '
                         f'could not convert "{parts[1]}" to an integer'
                     )

core/dbt/adapters/base/connections.py

@@ -2,6 +2,7 @@ import abc
 import os
 from time import sleep
 import sys
+import traceback
 
 # multiprocessing.RLock is a function returning this type
 from multiprocessing.synchronize import RLock
@@ -40,14 +41,16 @@ from dbt.events.functions import fire_event
 from dbt.events.types import (
     NewConnection,
     ConnectionReused,
+    ConnectionLeftOpenInCleanup,
     ConnectionLeftOpen,
-    ConnectionLeftOpen2,
+    ConnectionClosedInCleanup,
     ConnectionClosed,
-    ConnectionClosed2,
     Rollback,
     RollbackFailed,
 )
+from dbt.events.contextvars import get_node_info
 from dbt import flags
+from dbt.utils import cast_to_str
 
 SleepTime = Union[int, float]  # As taken by time.sleep.
 AdapterHandle = Any  # Adapter connection handle objects can be any class.
@@ -88,13 +91,13 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         key = self.get_thread_identifier()
         with self.lock:
             if key not in self.thread_connections:
-                raise dbt.exceptions.InvalidConnectionException(key, list(self.thread_connections))
+                raise dbt.exceptions.InvalidConnectionError(key, list(self.thread_connections))
             return self.thread_connections[key]
 
     def set_thread_connection(self, conn: Connection) -> None:
         key = self.get_thread_identifier()
         if key in self.thread_connections:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 "In set_thread_connection, existing connection exists for {}"
             )
         self.thread_connections[key] = conn
@@ -134,47 +137,49 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A context manager that handles exceptions raised by the
             underlying database.
         """
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`exception_handler` is not implemented for this adapter!"
         )
 
     def set_connection_name(self, name: Optional[str] = None) -> Connection:
-        conn_name: str
+        """Called by 'acquire_connection' in BaseAdapter, which is called by
-        if name is None:
+        'connection_named', called by 'connection_for(node)'.
-            # if a name isn't specified, we'll re-use a single handle
+        Creates a connection for this thread if one doesn't already
-            # named 'master'
+        exist, and will rename an existing connection."""
-            conn_name = "master"
-        else:
-            if not isinstance(name, str):
-                raise dbt.exceptions.CompilerException(
-                    f"For connection name, got {name} - not a string!"
-                )
-            assert isinstance(name, str)
-            conn_name = name
 
+        conn_name: str = "master" if name is None else name
+
+        # Get a connection for this thread
         conn = self.get_if_exists()
+
+        if conn and conn.name == conn_name and conn.state == "open":
+            # Found a connection and nothing to do, so just return it
+            return conn
+
         if conn is None:
+            # Create a new connection
             conn = Connection(
                 type=Identifier(self.TYPE),
-                name=None,
+                name=conn_name,
                 state=ConnectionState.INIT,
                 transaction_open=False,
                 handle=None,
                 credentials=self.profile.credentials,
             )
-            self.set_thread_connection(conn)
-
-        if conn.name == conn_name and conn.state == "open":
-            return conn
-
-        fire_event(NewConnection(conn_name=conn_name, conn_type=self.TYPE))
-
-        if conn.state == "open":
-            fire_event(ConnectionReused(conn_name=conn_name))
-        else:
             conn.handle = LazyHandle(self.open)
+            # Add the connection to thread_connections for this thread
+            self.set_thread_connection(conn)
+            fire_event(
+                NewConnection(conn_name=conn_name, conn_type=self.TYPE, node_info=get_node_info())
+            )
+        else:  # existing connection either wasn't open or didn't have the right name
+            if conn.state != "open":
+                conn.handle = LazyHandle(self.open)
+            if conn.name != conn_name:
+                orig_conn_name: str = conn.name or ""
+                conn.name = conn_name
+                fire_event(ConnectionReused(orig_conn_name=orig_conn_name, conn_name=conn_name))
 
-        conn.name = conn_name
         return conn
 
     @classmethod
@@ -206,7 +211,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             connect should trigger a retry.
         :type retryable_exceptions: Iterable[Type[Exception]]
         :param int retry_limit: How many times to retry the call to connect. If this limit
-            is exceeded before a successful call, a FailedToConnectException will be raised.
+            is exceeded before a successful call, a FailedToConnectError will be raised.
             Must be non-negative.
         :param retry_timeout: Time to wait between attempts to connect. Can also take a
             Callable that takes the number of attempts so far, beginning at 0, and returns an int
@@ -215,14 +220,14 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :param int _attempts: Parameter used to keep track of the number of attempts in calling the
             connect function across recursive calls. Passed as an argument to retry_timeout if it
             is a Callable. This parameter should not be set by the initial caller.
-        :raises dbt.exceptions.FailedToConnectException: Upon exhausting all retry attempts without
+        :raises dbt.exceptions.FailedToConnectError: Upon exhausting all retry attempts without
             successfully acquiring a handle.
         :return: The given connection with its appropriate state and handle attributes set
             depending on whether we successfully acquired a handle or not.
         """
         timeout = retry_timeout(_attempts) if callable(retry_timeout) else retry_timeout
         if timeout < 0:
-            raise dbt.exceptions.FailedToConnectException(
+            raise dbt.exceptions.FailedToConnectError(
                 "retry_timeout cannot be negative or return a negative time."
             )
 
@@ -230,7 +235,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             # This guard is not perfect others may add to the recursion limit (e.g. built-ins).
             connection.handle = None
             connection.state = ConnectionState.FAIL
-            raise dbt.exceptions.FailedToConnectException("retry_limit cannot be negative")
+            raise dbt.exceptions.FailedToConnectError("retry_limit cannot be negative")
 
         try:
             connection.handle = connect()
@@ -241,7 +246,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             if retry_limit <= 0:
                 connection.handle = None
                 connection.state = ConnectionState.FAIL
-                raise dbt.exceptions.FailedToConnectException(str(e))
+                raise dbt.exceptions.FailedToConnectError(str(e))
 
             logger.debug(
                 f"Got a retryable error when attempting to open a {cls.TYPE} connection.\n"
@@ -263,12 +268,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         except Exception as e:
             connection.handle = None
             connection.state = ConnectionState.FAIL
-            raise dbt.exceptions.FailedToConnectException(str(e))
+            raise dbt.exceptions.FailedToConnectError(str(e))
 
     @abc.abstractmethod
     def cancel_open(self) -> Optional[List[str]]:
         """Cancel all open connections on the adapter. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`cancel_open` is not implemented for this adapter!"
         )
 
@@ -283,7 +288,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         This should be thread-safe, or hold the lock if necessary. The given
         connection should not be in either in_use or available.
         """
-        raise dbt.exceptions.NotImplementedException("`open` is not implemented for this adapter!")
+        raise dbt.exceptions.NotImplementedError("`open` is not implemented for this adapter!")
 
     def release(self) -> None:
         with self.lock:
@@ -304,9 +309,9 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         with self.lock:
             for connection in self.thread_connections.values():
                 if connection.state not in {"closed", "init"}:
-                    fire_event(ConnectionLeftOpen(conn_name=connection.name))
+                    fire_event(ConnectionLeftOpenInCleanup(conn_name=cast_to_str(connection.name)))
                 else:
-                    fire_event(ConnectionClosed(conn_name=connection.name))
+                    fire_event(ConnectionClosedInCleanup(conn_name=cast_to_str(connection.name)))
                 self.close(connection)
 
             # garbage collect these connections
@@ -315,16 +320,12 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     def begin(self) -> None:
         """Begin a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError("`begin` is not implemented for this adapter!")
-            "`begin` is not implemented for this adapter!"
-        )
 
     @abc.abstractmethod
     def commit(self) -> None:
         """Commit a transaction. (passable)"""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError("`commit` is not implemented for this adapter!")
-            "`commit` is not implemented for this adapter!"
-        )
 
     @classmethod
     def _rollback_handle(cls, connection: Connection) -> None:
@@ -332,28 +333,40 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         try:
             connection.handle.rollback()
         except Exception:
-            fire_event(RollbackFailed(conn_name=connection.name))
+            fire_event(
+                RollbackFailed(
+                    conn_name=cast_to_str(connection.name),
+                    exc_info=traceback.format_exc(),
+                    node_info=get_node_info(),
+                )
+            )
 
     @classmethod
     def _close_handle(cls, connection: Connection) -> None:
         """Perform the actual close operation."""
         # On windows, sometimes connection handles don't have a close() attr.
         if hasattr(connection.handle, "close"):
-            fire_event(ConnectionClosed2(conn_name=connection.name))
+            fire_event(
+                ConnectionClosed(conn_name=cast_to_str(connection.name), node_info=get_node_info())
+            )
             connection.handle.close()
         else:
-            fire_event(ConnectionLeftOpen2(conn_name=connection.name))
+            fire_event(
+                ConnectionLeftOpen(
+                    conn_name=cast_to_str(connection.name), node_info=get_node_info()
+                )
+            )
 
     @classmethod
     def _rollback(cls, connection: Connection) -> None:
         """Roll back the given connection."""
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Tried to rollback transaction on connection "
                 f'"{connection.name}", but it does not have one open!'
             )
 
-        fire_event(Rollback(conn_name=connection.name))
+        fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
         cls._rollback_handle(connection)
 
         connection.transaction_open = False
@@ -365,7 +378,7 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
             return connection
 
         if connection.transaction_open and connection.handle:
-            fire_event(Rollback(conn_name=connection.name))
+            fire_event(Rollback(conn_name=cast_to_str(connection.name), node_info=get_node_info()))
             cls._rollback_handle(connection)
         connection.transaction_open = False
 
@@ -398,6 +411,4 @@ class BaseConnectionManager(metaclass=abc.ABCMeta):
         :return: A tuple of the query status and results (empty if fetch=False).
         :rtype: Tuple[AdapterResponse, agate.Table]
         """
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError("`execute` is not implemented for this adapter!")
-            "`execute` is not implemented for this adapter!"
-        )

core/dbt/adapters/base/impl.py

@@ -15,7 +15,6 @@ from typing import (
     List,
     Mapping,
     Iterator,
-    Union,
     Set,
 )
 
@@ -23,13 +22,20 @@ import agate
 import pytz
 
 from dbt.exceptions import (
-    raise_database_error,
+    DbtInternalError,
-    raise_compiler_error,
+    MacroArgTypeError,
-    invalid_type_error,
+    MacroResultError,
-    get_relation_returned_multiple_results,
+    QuoteConfigTypeError,
-    InternalException,
+    NotImplementedError,
-    NotImplementedException,
+    NullRelationCacheAttemptedError,
-    RuntimeException,
+    NullRelationDropAttemptedError,
+    RelationReturnedMultipleResultsError,
+    RenameToNoneAttemptedError,
+    DbtRuntimeError,
+    SnapshotTargetIncompleteError,
+    SnapshotTargetNotSnapshotTableError,
+    UnexpectedNullError,
+    UnexpectedNonTimestampError,
 )
 
 from dbt.adapters.protocol import (
@@ -38,18 +44,17 @@ from dbt.adapters.protocol import (
 )
 from dbt.clients.agate_helper import empty_table, merge_tables, table_from_rows
 from dbt.clients.jinja import MacroGenerator
-from dbt.contracts.graph.compiled import CompileResultNode, CompiledSeedNode
 from dbt.contracts.graph.manifest import Manifest, MacroManifest
-from dbt.contracts.graph.parsed import ParsedSeedNode
+from dbt.contracts.graph.nodes import ResultNode
-from dbt.exceptions import warn_or_error
+from dbt.events.functions import fire_event, warn_or_error
-from dbt.events.functions import fire_event
 from dbt.events.types import (
     CacheMiss,
     ListRelations,
     CodeExecution,
     CodeExecutionStatus,
+    CatalogGenerationError,
 )
-from dbt.utils import filter_null_values, executor
+from dbt.utils import filter_null_values, executor, cast_to_str
 
 from dbt.adapters.base.connections import Connection, AdapterResponse
 from dbt.adapters.base.meta import AdapterMeta, available
@@ -61,10 +66,7 @@ from dbt.adapters.base.relation import (
 )
 from dbt.adapters.base import Column as BaseColumn
 from dbt.adapters.base import Credentials
-from dbt.adapters.cache import RelationsCache, _make_key
+from dbt.adapters.cache import RelationsCache, _make_ref_key_msg
-
-
-SeedModel = Union[ParsedSeedNode, CompiledSeedNode]
 
 
 GET_CATALOG_MACRO_NAME = "get_catalog"
@@ -73,7 +75,7 @@ FRESHNESS_MACRO_NAME = "collect_freshness"
 
 def _expect_row_value(key: str, row: agate.Row):
     if key not in row.keys():
-        raise InternalException(
+        raise DbtInternalError(
             'Got a row without "{}" column, columns: {}'.format(key, row.keys())
         )
     return row[key]
@@ -102,18 +104,10 @@ def _utc(dt: Optional[datetime], source: BaseRelation, field_name: str) -> datet
     assume the datetime is already for UTC and add the timezone.
     """
     if dt is None:
-        raise raise_database_error(
+        raise UnexpectedNullError(field_name, source)
-            "Expected a non-null value when querying field '{}' of table "
-            " {} but received value 'null' instead".format(field_name, source)
-        )
 
     elif not hasattr(dt, "tzinfo"):
-        raise raise_database_error(
+        raise UnexpectedNonTimestampError(field_name, source, dt)
-            "Expected a timestamp value when querying field '{}' of table "
-            "{} but received value of type '{}' instead".format(
-                field_name, source, type(dt).__name__
-            )
-        )
 
     elif dt.tzinfo:
         return dt.astimezone(pytz.UTC)
@@ -243,9 +237,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         return conn.name
 
     @contextmanager
-    def connection_named(
+    def connection_named(self, name: str, node: Optional[ResultNode] = None) -> Iterator[None]:
-        self, name: str, node: Optional[CompileResultNode] = None
-    ) -> Iterator[None]:
         try:
             if self.connections.query_header is not None:
                 self.connections.query_header.set(name, node)
@@ -257,7 +249,7 @@ class BaseAdapter(metaclass=AdapterMeta):
                 self.connections.query_header.reset()
 
     @contextmanager
-    def connection_for(self, node: CompileResultNode) -> Iterator[None]:
+    def connection_for(self, node: ResultNode) -> Iterator[None]:
         with self.connection_named(node.unique_id, node):
             yield
 
@@ -343,7 +335,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             fire_event(
                 CacheMiss(
                     conn_name=self.nice_connection_name(),
-                    database=database,
+                    database=cast_to_str(database),
                     schema=schema,
                 )
             )
@@ -372,7 +364,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         lowercase strings.
         """
         info_schema_name_map = SchemaSearchMap()
-        nodes: Iterator[CompileResultNode] = chain(
+        nodes: Iterator[ResultNode] = chain(
             [
                 node
                 for node in manifest.nodes.values()
@@ -441,7 +433,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         """Cache a new relation in dbt. It will show up in `list relations`."""
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to cache a null relation for {}".format(name))
+            raise NullRelationCacheAttemptedError(name)
         self.cache.add(relation)
         # so jinja doesn't render things
         return ""
@@ -453,7 +445,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         """
         if relation is None:
             name = self.nice_connection_name()
-            raise_compiler_error("Attempted to drop a null relation for {}".format(name))
+            raise NullRelationDropAttemptedError(name)
         self.cache.drop(relation)
         return ""
 
@@ -470,9 +462,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             name = self.nice_connection_name()
             src_name = _relation_name(from_relation)
             dst_name = _relation_name(to_relation)
-            raise_compiler_error(
+            raise RenameToNoneAttemptedError(src_name, dst_name, name)
-                "Attempted to rename {} to {} for {}".format(src_name, dst_name, name)
-            )
 
         self.cache.rename(from_relation, to_relation)
         return ""
@@ -484,12 +474,12 @@ class BaseAdapter(metaclass=AdapterMeta):
     @abc.abstractmethod
     def date_function(cls) -> str:
         """Get the date function used by this adapter's database."""
-        raise NotImplementedException("`date_function` is not implemented for this adapter!")
+        raise NotImplementedError("`date_function` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
     def is_cancelable(cls) -> bool:
-        raise NotImplementedException("`is_cancelable` is not implemented for this adapter!")
+        raise NotImplementedError("`is_cancelable` is not implemented for this adapter!")
 
     ###
     # Abstract methods about schemas
@@ -497,7 +487,7 @@ class BaseAdapter(metaclass=AdapterMeta):
     @abc.abstractmethod
     def list_schemas(self, database: str) -> List[str]:
         """Get a list of existing schemas in database"""
-        raise NotImplementedException("`list_schemas` is not implemented for this adapter!")
+        raise NotImplementedError("`list_schemas` is not implemented for this adapter!")
 
     @available.parse(lambda *a, **k: False)
     def check_schema_exists(self, database: str, schema: str) -> bool:
@@ -520,13 +510,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         *Implementors must call self.cache.drop() to preserve cache state!*
         """
-        raise NotImplementedException("`drop_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def truncate_relation(self, relation: BaseRelation) -> None:
         """Truncate the given relation."""
-        raise NotImplementedException("`truncate_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`truncate_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
@@ -535,15 +525,13 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         Implementors must call self.cache.rename() to preserve cache state.
         """
-        raise NotImplementedException("`rename_relation` is not implemented for this adapter!")
+        raise NotImplementedError("`rename_relation` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_list
     def get_columns_in_relation(self, relation: BaseRelation) -> List[BaseColumn]:
         """Get a list of the columns in the given Relation."""
-        raise NotImplementedException(
+        raise NotImplementedError("`get_columns_in_relation` is not implemented for this adapter!")
-            "`get_columns_in_relation` is not implemented for this adapter!"
-        )
 
     @available.deprecated("get_columns_in_relation", lambda *a, **k: [])
     def get_columns_in_table(self, schema: str, identifier: str) -> List[BaseColumn]:
@@ -565,7 +553,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param self.Relation current: A relation that currently exists in the
             database with columns of unspecified types.
         """
-        raise NotImplementedException(
+        raise NotImplementedError(
             "`expand_target_column_types` is not implemented for this adapter!"
         )
 
@@ -580,8 +568,8 @@ class BaseAdapter(metaclass=AdapterMeta):
         :return: The relations in schema
         :rtype: List[self.Relation]
         """
-        raise NotImplementedException(
+        raise NotImplementedError(
-            "`list_relations_without_caching` is not implemented for this " "adapter!"
+            "`list_relations_without_caching` is not implemented for this adapter!"
         )
 
     ###
@@ -622,7 +610,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         to_relation.
         """
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -630,7 +618,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="get_missing_columns",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -651,11 +639,11 @@ class BaseAdapter(metaclass=AdapterMeta):
         expected columns.
 
         :param Relation relation: The relation to check
-        :raises CompilationException: If the columns are
+        :raises InvalidMacroArgType: If the columns are
             incorrect.
         """
         if not isinstance(relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="valid_snapshot_target",
                 arg_name="relation",
                 got_value=relation,
@@ -676,24 +664,16 @@ class BaseAdapter(metaclass=AdapterMeta):
 
         if missing:
             if extra:
-                msg = (
+                raise SnapshotTargetIncompleteError(extra, missing)
-                    'Snapshot target has ("{}") but not ("{}") - is it an '
-                    "unmigrated previous version archive?".format(
-                        '", "'.join(extra), '", "'.join(missing)
-                    )
-                )
             else:
-                msg = 'Snapshot target is not a snapshot table (missing "{}")'.format(
+                raise SnapshotTargetNotSnapshotTableError(missing)
-                    '", "'.join(missing)
-                )
-            raise_compiler_error(msg)
 
     @available.parse_none
     def expand_target_column_types(
         self, from_relation: BaseRelation, to_relation: BaseRelation
     ) -> None:
         if not isinstance(from_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="from_relation",
                 got_value=from_relation,
@@ -701,7 +681,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             )
 
         if not isinstance(to_relation, self.Relation):
-            invalid_type_error(
+            raise MacroArgTypeError(
                 method_name="expand_target_column_types",
                 arg_name="to_relation",
                 got_value=to_relation,
@@ -726,9 +706,9 @@ class BaseAdapter(metaclass=AdapterMeta):
         relations = self.list_relations_without_caching(schema_relation)
         fire_event(
             ListRelations(
-                database=database,
+                database=cast_to_str(database),
                 schema=schema,
-                relations=[_make_key(x) for x in relations],
+                relations=[_make_ref_key_msg(x) for x in relations],
             )
         )
 
@@ -783,7 +763,7 @@ class BaseAdapter(metaclass=AdapterMeta):
                 "schema": schema,
                 "database": database,
             }
-            get_relation_returned_multiple_results(kwargs, matches)
+            raise RelationReturnedMultipleResultsError(kwargs, matches)
 
         elif matches:
             return matches[0]
@@ -805,20 +785,20 @@ class BaseAdapter(metaclass=AdapterMeta):
     @available.parse_none
     def create_schema(self, relation: BaseRelation):
         """Create the given schema if it does not exist."""
-        raise NotImplementedException("`create_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`create_schema` is not implemented for this adapter!")
 
     @abc.abstractmethod
     @available.parse_none
     def drop_schema(self, relation: BaseRelation):
         """Drop the given schema (and everything in it) if it exists."""
-        raise NotImplementedException("`drop_schema` is not implemented for this adapter!")
+        raise NotImplementedError("`drop_schema` is not implemented for this adapter!")
 
     @available
     @classmethod
     @abc.abstractmethod
     def quote(cls, identifier: str) -> str:
         """Quote the given identifier, as appropriate for the database."""
-        raise NotImplementedException("`quote` is not implemented for this adapter!")
+        raise NotImplementedError("`quote` is not implemented for this adapter!")
 
     @available
     def quote_as_configured(self, identifier: str, quote_key: str) -> str:
@@ -847,10 +827,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif quote_config is None:
             pass
         else:
-            raise_compiler_error(
+            raise QuoteConfigTypeError(quote_config)
-                f'The seed configuration value of "quote_columns" has an '
-                f"invalid type {type(quote_config)}"
-            )
 
         if quote_columns:
             return self.quote(column)
@@ -871,7 +848,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_text_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_text_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -883,7 +860,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_number_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_number_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -895,9 +872,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
+        raise NotImplementedError("`convert_boolean_type` is not implemented for this adapter!")
-            "`convert_boolean_type` is not implemented for this adapter!"
-        )
 
     @classmethod
     @abc.abstractmethod
@@ -909,9 +884,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException(
+        raise NotImplementedError("`convert_datetime_type` is not implemented for this adapter!")
-            "`convert_datetime_type` is not implemented for this adapter!"
-        )
 
     @classmethod
     @abc.abstractmethod
@@ -923,7 +896,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_date_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_date_type` is not implemented for this adapter!")
 
     @classmethod
     @abc.abstractmethod
@@ -935,7 +908,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         :param col_idx: The index into the agate table for the column.
         :return: The name of the type in the database
         """
-        raise NotImplementedException("`convert_time_type` is not implemented for this adapter!")
+        raise NotImplementedError("`convert_time_type` is not implemented for this adapter!")
 
     @available
     @classmethod
@@ -1002,7 +975,7 @@ class BaseAdapter(metaclass=AdapterMeta):
             else:
                 package_name = 'the "{}" package'.format(project)
 
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 'dbt could not find a macro with the name "{}" in {}'.format(
                     macro_name, package_name
                 )
@@ -1100,11 +1073,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         # now we have a 1-row table of the maximum `loaded_at_field` value and
         # the current time according to the db.
         if len(table) != 1 or len(table[0]) != 2:
-            raise_compiler_error(
+            raise MacroResultError(FRESHNESS_MACRO_NAME, table)
-                'Got an invalid result from "{}" macro: {}'.format(
-                    FRESHNESS_MACRO_NAME, [tuple(r) for r in table]
-                )
-            )
         if table[0][0] is None:
             # no records in the table, so really the max_loaded_at was
             # infinitely long ago. Just call it 0:00 January 1 year UTC
@@ -1181,7 +1150,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         elif location == "prepend":
             return f"'{value}' || {add_to}"
         else:
-            raise RuntimeException(f'Got an unexpected location value of "{location}"')
+            raise DbtRuntimeError(f'Got an unexpected location value of "{location}"')
 
     def get_rows_different_sql(
         self,
@@ -1239,7 +1208,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         return self.generate_python_submission_response(submission_result)
 
     def generate_python_submission_response(self, submission_result: Any) -> AdapterResponse:
-        raise NotImplementedException(
+        raise NotImplementedError(
             "Your adapter need to implement generate_python_submission_response"
         )
 
@@ -1263,7 +1232,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         valid_strategies.append("default")
         builtin_strategies = self.builtin_incremental_strategies()
         if strategy in builtin_strategies and strategy not in valid_strategies:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"The incremental strategy '{strategy}' is not valid for this adapter"
             )
 
@@ -1271,7 +1240,7 @@ class BaseAdapter(metaclass=AdapterMeta):
         macro_name = f"get_incremental_{strategy}_sql"
         # The model_context should have MacroGenerator callable objects for all macros
         if macro_name not in model_context:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 'dbt could not find an incremental strategy macro with the name "{}" in {}'.format(
                     macro_name, self.config.project_name
                 )
@@ -1327,7 +1296,7 @@ def catch_as_completed(
         elif isinstance(exc, KeyboardInterrupt) or not isinstance(exc, Exception):
             raise exc
         else:
-            warn_or_error(f"Encountered an error while generating catalog: {str(exc)}")
+            warn_or_error(CatalogGenerationError(exc=str(exc)))
             # exc is not None, derives from Exception, and isn't ctrl+c
             exceptions.append(exc)
     return merge_tables(tables), exceptions

core/dbt/adapters/base/plugin.py

@@ -1,7 +1,7 @@
 from typing import List, Optional, Type
 
 from dbt.adapters.base import Credentials
-from dbt.exceptions import CompilationException
+from dbt.exceptions import CompilationError
 from dbt.adapters.protocol import AdapterProtocol
 
 
@@ -11,7 +11,7 @@ def project_name_from_path(include_path: str) -> str:
 
     partial = Project.partial_load(include_path)
     if partial.project_name is None:
-        raise CompilationException(f"Invalid project at {include_path}: name not set!")
+        raise CompilationError(f"Invalid project at {include_path}: name not set!")
     return partial.project_name
 
 

core/dbt/adapters/base/query_headers.py

@@ -5,9 +5,9 @@ from dbt.clients.jinja import QueryStringGenerator
 
 from dbt.context.manifest import generate_query_header_context
 from dbt.contracts.connection import AdapterRequiredConfig, QueryComment
-from dbt.contracts.graph.compiled import CompileResultNode
+from dbt.contracts.graph.nodes import ResultNode
 from dbt.contracts.graph.manifest import Manifest
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 class NodeWrapper:
@@ -48,7 +48,7 @@ class _QueryComment(local):
         if isinstance(comment, str) and "*/" in comment:
             # tell the user "no" so they don't hurt themselves by writing
             # garbage
-            raise RuntimeException(f'query comment contains illegal value "*/": {comment}')
+            raise DbtRuntimeError(f'query comment contains illegal value "*/": {comment}')
         self.query_comment = comment
         self.append = append
 
@@ -90,7 +90,7 @@ class MacroQueryStringSetter:
     def reset(self):
         self.set("master", None)
 
-    def set(self, name: str, node: Optional[CompileResultNode]):
+    def set(self, name: str, node: Optional[ResultNode]):
         wrapped: Optional[NodeWrapper] = None
         if node is not None:
             wrapped = NodeWrapper(node)

core/dbt/adapters/base/relation.py

@@ -1,9 +1,8 @@
 from collections.abc import Hashable
-from dataclasses import dataclass
+from dataclasses import dataclass, field
-from typing import Optional, TypeVar, Any, Type, Dict, Union, Iterator, Tuple, Set
+from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set
 
-from dbt.contracts.graph.compiled import CompiledNode
+from dbt.contracts.graph.nodes import SourceDefinition, ManifestNode, ResultNode, ParsedNode
-from dbt.contracts.graph.parsed import ParsedSourceDefinition, ParsedNode
 from dbt.contracts.relation import (
     RelationType,
     ComponentName,
@@ -12,7 +11,11 @@ from dbt.contracts.relation import (
     Policy,
     Path,
 )
-from dbt.exceptions import InternalException
+from dbt.exceptions import (
+    ApproximateMatchError,
+    DbtInternalError,
+    MultipleDatabasesNotAllowedError,
+)
 from dbt.node_types import NodeType
 from dbt.utils import filter_null_values, deep_merge, classproperty
 
@@ -27,8 +30,10 @@ class BaseRelation(FakeAPIObject, Hashable):
     path: Path
     type: Optional[RelationType] = None
     quote_character: str = '"'
-    include_policy: Policy = Policy()
+    # Python 3.11 requires that these use default_factory instead of simple default
-    quote_policy: Policy = Policy()
+    # ValueError: mutable default <class 'dbt.contracts.relation.Policy'> for field include_policy is not allowed: use default_factory
+    include_policy: Policy = field(default_factory=lambda: Policy())
+    quote_policy: Policy = field(default_factory=lambda: Policy())
     dbt_created: bool = False
 
     def _is_exactish_match(self, field: ComponentName, value: str) -> bool:
@@ -39,9 +44,9 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     @classmethod
     def _get_field_named(cls, field_name):
-        for field, _ in cls._get_fields():
+        for f, _ in cls._get_fields():
-            if field.name == field_name:
+            if f.name == field_name:
-                return field
+                return f
         # this should be unreachable
         raise ValueError(f"BaseRelation has no {field_name} field!")
 
@@ -52,11 +57,11 @@ class BaseRelation(FakeAPIObject, Hashable):
 
     @classmethod
     def get_default_quote_policy(cls) -> Policy:
-        return cls._get_field_named("quote_policy").default
+        return cls._get_field_named("quote_policy").default_factory()
 
     @classmethod
     def get_default_include_policy(cls) -> Policy:
-        return cls._get_field_named("include_policy").default
+        return cls._get_field_named("include_policy").default_factory()
 
     def get(self, key, default=None):
         """Override `.get` to return a metadata object so we don't break
@@ -82,7 +87,7 @@ class BaseRelation(FakeAPIObject, Hashable):
 
         if not search:
             # nothing was passed in
-            raise dbt.exceptions.RuntimeException(
+            raise dbt.exceptions.DbtRuntimeError(
                 "Tried to match relation, but no search path was passed!"
             )
 
@@ -99,7 +104,7 @@ class BaseRelation(FakeAPIObject, Hashable):
 
         if approximate_match and not exact_match:
             target = self.create(database=database, schema=schema, identifier=identifier)
-            dbt.exceptions.approximate_relation_match(target, self)
+            raise ApproximateMatchError(target, self)
 
         return exact_match
 
@@ -184,7 +189,7 @@ class BaseRelation(FakeAPIObject, Hashable):
         )
 
     @classmethod
-    def create_from_source(cls: Type[Self], source: ParsedSourceDefinition, **kwargs: Any) -> Self:
+    def create_from_source(cls: Type[Self], source: SourceDefinition, **kwargs: Any) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
         source_quoting.pop("column", None)
         quote_policy = deep_merge(
@@ -209,7 +214,7 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_ephemeral_from_node(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[ParsedNode, CompiledNode],
+        node: ManifestNode,
     ) -> Self:
         # Note that ephemeral models are based on the name.
         identifier = cls.add_ephemeral_prefix(node.name)
@@ -222,7 +227,7 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_from_node(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[ParsedNode, CompiledNode],
+        node: ManifestNode,
         quote_policy: Optional[Dict[str, bool]] = None,
         **kwargs: Any,
     ) -> Self:
@@ -243,20 +248,20 @@ class BaseRelation(FakeAPIObject, Hashable):
     def create_from(
         cls: Type[Self],
         config: HasQuoting,
-        node: Union[CompiledNode, ParsedNode, ParsedSourceDefinition],
+        node: ResultNode,
         **kwargs: Any,
     ) -> Self:
         if node.resource_type == NodeType.Source:
-            if not isinstance(node, ParsedSourceDefinition):
+            if not isinstance(node, SourceDefinition):
-                raise InternalException(
+                raise DbtInternalError(
-                    "type mismatch, expected ParsedSourceDefinition but got {}".format(type(node))
+                    "type mismatch, expected SourceDefinition but got {}".format(type(node))
                 )
             return cls.create_from_source(node, **kwargs)
         else:
-            if not isinstance(node, (ParsedNode, CompiledNode)):
+            # Can't use ManifestNode here because of parameterized generics
-                raise InternalException(
+            if not isinstance(node, (ParsedNode)):
-                    "type mismatch, expected ParsedNode or CompiledNode but "
+                raise DbtInternalError(
-                    "got {}".format(type(node))
+                    f"type mismatch, expected ManifestNode but got {type(node)}"
                 )
             return cls.create_from_node(config, node, **kwargs)
 
@@ -353,7 +358,7 @@ class InformationSchema(BaseRelation):
 
     def __post_init__(self):
         if not isinstance(self.information_schema_view, (type(None), str)):
-            raise dbt.exceptions.CompilationException(
+            raise dbt.exceptions.CompilationError(
                 "Got an invalid name: {}".format(self.information_schema_view)
             )
 
@@ -437,7 +442,7 @@ class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
         if not allow_multiple_databases:
             seen = {r.database.lower() for r in self if r.database}
             if len(seen) > 1:
-                dbt.exceptions.raise_compiler_error(str(seen))
+                raise MultipleDatabasesNotAllowedError(seen)
 
         for information_schema_name, schema in self.search():
             path = {"database": information_schema_name.database, "schema": schema}

core/dbt/adapters/cache.py

@@ -1,28 +1,24 @@
-import re
 import threading
 from copy import deepcopy
 from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
 
-from dbt.adapters.reference_keys import _make_key, _ReferenceKey
+from dbt.adapters.reference_keys import (
-import dbt.exceptions
+    _make_ref_key,
-from dbt.events.functions import fire_event
+    _make_ref_key_msg,
-from dbt.events.types import (
+    _make_msg_from_ref_key,
-    AddLink,
+    _ReferenceKey,
-    AddRelation,
-    DropCascade,
-    DropMissingRelation,
-    DropRelation,
-    DumpAfterAddGraph,
-    DumpAfterRenameSchema,
-    DumpBeforeAddGraph,
-    DumpBeforeRenameSchema,
-    RenameSchema,
-    TemporaryRelation,
-    UncachedRelation,
-    UpdateReference,
 )
+from dbt.exceptions import (
+    DependentLinkNotCachedError,
+    NewNameAlreadyInCacheError,
+    NoneRelationFoundError,
+    ReferencedLinkNotCachedError,
+    TruncatedModelNameCausedCollisionError,
+)
+from dbt.events.functions import fire_event, fire_event_if
+from dbt.events.types import CacheAction, CacheDumpGraph
+import dbt.flags as flags
 from dbt.utils import lowercase
-from dbt.helper_types import Lazy
 
 
 def dot_separated(key: _ReferenceKey) -> str:
@@ -82,7 +78,7 @@ class _CachedRelation:
 
         :return _ReferenceKey: A key for this relation.
         """
-        return _make_key(self)
+        return _make_ref_key(self)
 
     def add_reference(self, referrer: "_CachedRelation"):
         """Add a reference from referrer to self, indicating that if this node
@@ -145,11 +141,7 @@ class _CachedRelation:
         :raises InternalError: If the new key already exists.
         """
         if new_key in self.referenced_by:
-            dbt.exceptions.raise_cache_inconsistent(
+            raise NewNameAlreadyInCacheError(old_key, new_key)
-                'in rename of "{}" -> "{}", new name is in the cache already'.format(
-                    old_key, new_key
-                )
-            )
 
         if old_key not in self.referenced_by:
             return
@@ -265,21 +257,17 @@ class RelationsCache:
         if referenced is None:
             return
         if referenced is None:
-            dbt.exceptions.raise_cache_inconsistent(
+            raise ReferencedLinkNotCachedError(referenced_key)
-                "in add_link, referenced link key {} not in cache!".format(referenced_key)
-            )
 
         dependent = self.relations.get(dependent_key)
         if dependent is None:
-            dbt.exceptions.raise_cache_inconsistent(
+            raise DependentLinkNotCachedError(dependent_key)
-                "in add_link, dependent link key {} not in cache!".format(dependent_key)
-            )
 
         assert dependent is not None  # we just raised!
 
         referenced.add_reference(dependent)
 
-    # TODO: Is this dead code?  I can't seem to find it grepping the codebase.
+    # This is called in plugins/postgres/dbt/adapters/postgres/impl.py
     def add_link(self, referenced, dependent):
         """Add a link between two relations to the database. If either relation
         does not exist, it will be added as an "external" relation.
@@ -294,13 +282,18 @@ class RelationsCache:
         :param BaseRelation dependent: The dependent model.
         :raises InternalError: If either entry does not exist.
         """
-        ref_key = _make_key(referenced)
+        ref_key = _make_ref_key(referenced)
-        dep_key = _make_key(dependent)
+        dep_key = _make_ref_key(dependent)
         if (ref_key.database, ref_key.schema) not in self:
             # if we have not cached the referenced schema at all, we must be
             # referring to a table outside our control. There's no need to make
             # a link - we will never drop the referenced relation during a run.
-            fire_event(UncachedRelation(dep_key=dep_key, ref_key=ref_key))
+            fire_event(
+                CacheAction(
+                    ref_key=_make_msg_from_ref_key(ref_key),
+                    ref_key_2=_make_msg_from_ref_key(dep_key),
+                )
+            )
             return
         if ref_key not in self.relations:
             # Insert a dummy "external" relation.
@@ -310,7 +303,13 @@ class RelationsCache:
             # Insert a dummy "external" relation.
             dependent = dependent.replace(type=referenced.External)
             self.add(dependent)
-        fire_event(AddLink(dep_key=dep_key, ref_key=ref_key))
+        fire_event(
+            CacheAction(
+                action="add_link",
+                ref_key=_make_msg_from_ref_key(dep_key),
+                ref_key_2=_make_msg_from_ref_key(ref_key),
+            )
+        )
         with self.lock:
             self._add_link(ref_key, dep_key)
 
@@ -321,12 +320,18 @@ class RelationsCache:
         :param BaseRelation relation: The underlying relation.
         """
         cached = _CachedRelation(relation)
-        fire_event(AddRelation(relation=_make_key(cached)))
+        fire_event_if(
-        fire_event(DumpBeforeAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="adding", dump=self.dump_graph()),
+        )
+        fire_event(CacheAction(action="add_relation", ref_key=_make_ref_key_msg(cached)))
 
         with self.lock:
             self._setdefault(cached)
-        fire_event(DumpAfterAddGraph(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="adding", dump=self.dump_graph()),
+        )
 
     def _remove_refs(self, keys):
         """Removes all references to all entries in keys. This does not
@@ -341,19 +346,6 @@ class RelationsCache:
         for cached in self.relations.values():
             cached.release_references(keys)
 
-    def _drop_cascade_relation(self, dropped_key):
-        """Drop the given relation and cascade it appropriately to all
-        dependent relations.
-
-        :param _CachedRelation dropped: An existing _CachedRelation to drop.
-        """
-        if dropped_key not in self.relations:
-            fire_event(DropMissingRelation(relation=dropped_key))
-            return
-        consequences = self.relations[dropped_key].collect_consequences()
-        fire_event(DropCascade(dropped=dropped_key, consequences=consequences))
-        self._remove_refs(consequences)
-
     def drop(self, relation):
         """Drop the named relation and cascade it appropriately to all
         dependent relations.
@@ -365,10 +357,22 @@ class RelationsCache:
         :param str schema: The schema of the relation to drop.
         :param str identifier: The identifier of the relation to drop.
         """
-        dropped_key = _make_key(relation)
+        dropped_key = _make_ref_key(relation)
-        fire_event(DropRelation(dropped=dropped_key))
+        dropped_key_msg = _make_ref_key_msg(relation)
+        fire_event(CacheAction(action="drop_relation", ref_key=dropped_key_msg))
         with self.lock:
-            self._drop_cascade_relation(dropped_key)
+            if dropped_key not in self.relations:
+                fire_event(CacheAction(action="drop_missing_relation", ref_key=dropped_key_msg))
+                return
+            consequences = self.relations[dropped_key].collect_consequences()
+            # convert from a list of _ReferenceKeys to a list of ReferenceKeyMsgs
+            consequence_msgs = [_make_msg_from_ref_key(key) for key in consequences]
+            fire_event(
+                CacheAction(
+                    action="drop_cascade", ref_key=dropped_key_msg, ref_list=consequence_msgs
+                )
+            )
+            self._remove_refs(consequences)
 
     def _rename_relation(self, old_key, new_relation):
         """Rename a relation named old_key to new_key, updating references.
@@ -390,8 +394,14 @@ class RelationsCache:
         for cached in self.relations.values():
             if cached.is_referenced_by(old_key):
                 fire_event(
-                    UpdateReference(old_key=old_key, new_key=new_key, cached_key=cached.key())
+                    CacheAction(
+                        action="update_reference",
+                        ref_key=_make_ref_key_msg(old_key),
+                        ref_key_2=_make_ref_key_msg(new_key),
+                        ref_key_3=_make_ref_key_msg(cached.key()),
+                    )
                 )
+
                 cached.rename_key(old_key, new_key)
 
         self.relations[new_key] = relation
@@ -416,27 +426,12 @@ class RelationsCache:
         if new_key in self.relations:
             # Tell user when collision caused by model names truncated during
             # materialization.
-            match = re.search("__dbt_backup|__dbt_tmp$", new_key.identifier)
+            raise TruncatedModelNameCausedCollisionError(new_key, self.relations)
-            if match:
-                truncated_model_name_prefix = new_key.identifier[: match.start()]
-                message_addendum = (
-                    "\n\nName collisions can occur when the length of two "
-                    "models' names approach your database's builtin limit. "
-                    "Try restructuring your project such that no two models "
-                    "share the prefix '{}'.".format(truncated_model_name_prefix)
-                    + " Then, clean your warehouse of any removed models."
-                )
-            else:
-                message_addendum = ""
-
-            dbt.exceptions.raise_cache_inconsistent(
-                "in rename, new key {} already in cache: {}{}".format(
-                    new_key, list(self.relations.keys()), message_addendum
-                )
-            )
 
         if old_key not in self.relations:
-            fire_event(TemporaryRelation(key=old_key))
+            fire_event(
+                CacheAction(action="temporary_relation", ref_key=_make_msg_from_ref_key(old_key))
+            )
             return False
         return True
 
@@ -452,11 +447,20 @@ class RelationsCache:
         :param BaseRelation new: The new relation name information.
         :raises InternalError: If the new key is already present.
         """
-        old_key = _make_key(old)
+        old_key = _make_ref_key(old)
-        new_key = _make_key(new)
+        new_key = _make_ref_key(new)
-        fire_event(RenameSchema(old_key=old_key, new_key=new_key))
+        fire_event(
+            CacheAction(
+                action="rename_relation",
+                ref_key=_make_msg_from_ref_key(old_key),
+                ref_key_2=_make_msg_from_ref_key(new),
+            )
+        )
 
-        fire_event(DumpBeforeRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="before", action="rename", dump=self.dump_graph()),
+        )
 
         with self.lock:
             if self._check_rename_constraints(old_key, new_key):
@@ -464,7 +468,10 @@ class RelationsCache:
             else:
                 self._setdefault(_CachedRelation(new))
 
-        fire_event(DumpAfterRenameSchema(dump=Lazy.defer(lambda: self.dump_graph())))
+        fire_event_if(
+            flags.LOG_CACHE_EVENTS,
+            lambda: CacheDumpGraph(before_after="after", action="rename", dump=self.dump_graph()),
+        )
 
     def get_relations(self, database: Optional[str], schema: Optional[str]) -> List[Any]:
         """Case-insensitively yield all relations matching the given schema.
@@ -483,9 +490,7 @@ class RelationsCache:
             ]
 
         if None in results:
-            dbt.exceptions.raise_cache_inconsistent(
+            raise NoneRelationFoundError()
-                "in get_relations, a None relation was found in the cache!"
-            )
         return results
 
     def clear(self):
@@ -512,6 +517,6 @@ class RelationsCache:
         """
         for relation in to_remove:
             # it may have been cascaded out already
-            drop_key = _make_key(relation)
+            drop_key = _make_ref_key(relation)
             if drop_key in self.relations:
                 self.drop(drop_key)

core/dbt/adapters/factory.py

@@ -1,4 +1,5 @@
 import threading
+import traceback
 from contextlib import contextmanager
 from importlib import import_module
 from pathlib import Path
@@ -9,7 +10,7 @@ from dbt.adapters.protocol import AdapterConfig, AdapterProtocol, RelationProtoc
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.events.functions import fire_event
 from dbt.events.types import AdapterImportError, PluginLoadError
-from dbt.exceptions import InternalException, RuntimeException
+from dbt.exceptions import DbtInternalError, DbtRuntimeError
 from dbt.include.global_project import PACKAGE_PATH as GLOBAL_PROJECT_PATH
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
 
@@ -33,7 +34,7 @@ class AdapterContainer:
             names = ", ".join(self.plugins.keys())
 
         message = f"Invalid adapter type {name}! Must be one of {names}"
-        raise RuntimeException(message)
+        raise DbtRuntimeError(message)
 
     def get_adapter_class_by_name(self, name: str) -> Type[Adapter]:
         plugin = self.get_plugin_by_name(name)
@@ -59,17 +60,17 @@ class AdapterContainer:
             # the user about it via a runtime error
             if exc.name == "dbt.adapters." + name:
                 fire_event(AdapterImportError(exc=str(exc)))
-                raise RuntimeException(f"Could not find adapter type {name}!")
+                raise DbtRuntimeError(f"Could not find adapter type {name}!")
             # otherwise, the error had to have come from some underlying
             # library. Log the stack trace.
 
-            fire_event(PluginLoadError())
+            fire_event(PluginLoadError(exc_info=traceback.format_exc()))
             raise
         plugin: AdapterPlugin = mod.Plugin
         plugin_type = plugin.adapter.type()
 
         if plugin_type != name:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Expected to find adapter with type named {name}, got "
                 f"adapter with type {plugin_type}"
             )
@@ -131,7 +132,7 @@ class AdapterContainer:
             try:
                 plugin = self.plugins[plugin_name]
             except KeyError:
-                raise InternalException(f"No plugin found for {plugin_name}") from None
+                raise DbtInternalError(f"No plugin found for {plugin_name}") from None
             plugins.append(plugin)
             seen.add(plugin_name)
             for dep in plugin.dependencies:
@@ -150,7 +151,7 @@ class AdapterContainer:
             try:
                 path = self.packages[package_name]
             except KeyError:
-                raise InternalException(f"No internal package listing found for {package_name}")
+                raise DbtInternalError(f"No internal package listing found for {package_name}")
             paths.append(path)
         return paths
 

core/dbt/adapters/protocol.py

@@ -8,7 +8,6 @@ from typing import (
     Generic,
     TypeVar,
     Tuple,
-    Union,
     Dict,
     Any,
 )
@@ -17,8 +16,7 @@ from typing_extensions import Protocol
 import agate
 
 from dbt.contracts.connection import Connection, AdapterRequiredConfig, AdapterResponse
-from dbt.contracts.graph.compiled import CompiledNode, ManifestNode, NonSourceCompiledNode
+from dbt.contracts.graph.nodes import ResultNode, ManifestNode
-from dbt.contracts.graph.parsed import ParsedNode, ParsedSourceDefinition
 from dbt.contracts.graph.model_config import BaseConfig
 from dbt.contracts.graph.manifest import Manifest
 from dbt.contracts.relation import Policy, HasQuoting
@@ -48,11 +46,7 @@ class RelationProtocol(Protocol):
         ...
 
     @classmethod
-    def create_from(
+    def create_from(cls: Type[Self], config: HasQuoting, node: ResultNode) -> Self:
-        cls: Type[Self],
-        config: HasQuoting,
-        node: Union[CompiledNode, ParsedNode, ParsedSourceDefinition],
-    ) -> Self:
         ...
 
 
@@ -65,7 +59,7 @@ class CompilerProtocol(Protocol):
         node: ManifestNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestNode:
         ...
 
 

core/dbt/adapters/reference_keys.py

@@ -2,6 +2,7 @@
 
 from collections import namedtuple
 from typing import Any, Optional
+from dbt.events.proto_types import ReferenceKeyMsg
 
 
 _ReferenceKey = namedtuple("_ReferenceKey", "database schema identifier")
@@ -14,7 +15,12 @@ def lowercase(value: Optional[str]) -> Optional[str]:
         return value.lower()
 
 
+# For backwards compatibility. New code should use _make_ref_key
 def _make_key(relation: Any) -> _ReferenceKey:
+    return _make_ref_key(relation)
+
+
+def _make_ref_key(relation: Any) -> _ReferenceKey:
     """Make _ReferenceKeys with lowercase values for the cache so we don't have
     to keep track of quoting
     """
@@ -22,3 +28,13 @@ def _make_key(relation: Any) -> _ReferenceKey:
     return _ReferenceKey(
         lowercase(relation.database), lowercase(relation.schema), lowercase(relation.identifier)
     )
+
+
+def _make_ref_key_msg(relation: Any):
+    return _make_msg_from_ref_key(_make_ref_key(relation))
+
+
+def _make_msg_from_ref_key(ref_key: _ReferenceKey) -> ReferenceKeyMsg:
+    return ReferenceKeyMsg(
+        database=ref_key.database, schema=ref_key.schema, identifier=ref_key.identifier
+    )

core/dbt/adapters/sql/connections.py

@@ -10,6 +10,8 @@ from dbt.adapters.base import BaseConnectionManager
 from dbt.contracts.connection import Connection, ConnectionState, AdapterResponse
 from dbt.events.functions import fire_event
 from dbt.events.types import ConnectionUsed, SQLQuery, SQLCommit, SQLQueryStatus
+from dbt.events.contextvars import get_node_info
+from dbt.utils import cast_to_str
 
 
 class SQLConnectionManager(BaseConnectionManager):
@@ -25,9 +27,7 @@ class SQLConnectionManager(BaseConnectionManager):
     @abc.abstractmethod
     def cancel(self, connection: Connection):
         """Cancel the given connection."""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError("`cancel` is not implemented for this adapter!")
-            "`cancel` is not implemented for this adapter!"
-        )
 
     def cancel_open(self) -> List[str]:
         names = []
@@ -55,7 +55,13 @@ class SQLConnectionManager(BaseConnectionManager):
         connection = self.get_thread_connection()
         if auto_begin and connection.transaction_open is False:
             self.begin()
-        fire_event(ConnectionUsed(conn_type=self.TYPE, conn_name=connection.name))
+        fire_event(
+            ConnectionUsed(
+                conn_type=self.TYPE,
+                conn_name=cast_to_str(connection.name),
+                node_info=get_node_info(),
+            )
+        )
 
         with self.exception_handler(sql):
             if abridge_sql_log:
@@ -63,7 +69,11 @@ class SQLConnectionManager(BaseConnectionManager):
             else:
                 log_sql = sql
 
-            fire_event(SQLQuery(conn_name=connection.name, sql=log_sql))
+            fire_event(
+                SQLQuery(
+                    conn_name=cast_to_str(connection.name), sql=log_sql, node_info=get_node_info()
+                )
+            )
             pre = time.time()
 
             cursor = connection.handle.cursor()
@@ -71,7 +81,9 @@ class SQLConnectionManager(BaseConnectionManager):
 
             fire_event(
                 SQLQueryStatus(
-                    status=str(self.get_response(cursor)), elapsed=round((time.time() - pre), 2)
+                    status=str(self.get_response(cursor)),
+                    elapsed=round((time.time() - pre)),
+                    node_info=get_node_info(),
                 )
             )
 
@@ -81,7 +93,7 @@ class SQLConnectionManager(BaseConnectionManager):
     @abc.abstractmethod
     def get_response(cls, cursor: Any) -> AdapterResponse:
         """Get the status of the cursor."""
-        raise dbt.exceptions.NotImplementedException(
+        raise dbt.exceptions.NotImplementedError(
             "`get_response` is not implemented for this adapter!"
         )
 
@@ -137,7 +149,7 @@ class SQLConnectionManager(BaseConnectionManager):
     def begin(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is True:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to begin a new transaction on connection "{}", but '
                 "it already had one open!".format(connection.name)
             )
@@ -150,12 +162,12 @@ class SQLConnectionManager(BaseConnectionManager):
     def commit(self):
         connection = self.get_thread_connection()
         if connection.transaction_open is False:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 'Tried to commit transaction on connection "{}", but '
                 "it does not have one open!".format(connection.name)
             )
 
-        fire_event(SQLCommit(conn_name=connection.name))
+        fire_event(SQLCommit(conn_name=connection.name, node_info=get_node_info()))
         self.add_commit_query()
 
         connection.transaction_open = False

core/dbt/adapters/sql/impl.py

@@ -1,11 +1,10 @@
 import agate
 from typing import Any, Optional, Tuple, Type, List
 
-import dbt.clients.agate_helper
 from dbt.contracts.connection import Connection
-import dbt.exceptions
+from dbt.exceptions import RelationTypeNullError
 from dbt.adapters.base import BaseAdapter, available
-from dbt.adapters.cache import _make_key
+from dbt.adapters.cache import _make_ref_key_msg
 from dbt.adapters.sql import SQLConnectionManager
 from dbt.events.functions import fire_event
 from dbt.events.types import ColTypeChange, SchemaCreation, SchemaDrop
@@ -110,7 +109,7 @@ class SQLAdapter(BaseAdapter):
                     ColTypeChange(
                         orig_type=target_column.data_type,
                         new_type=new_type,
-                        table=_make_key(current),
+                        table=_make_ref_key_msg(current),
                     )
                 )
 
@@ -132,9 +131,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_relation(self, relation):
         if relation.type is None:
-            dbt.exceptions.raise_compiler_error(
+            raise RelationTypeNullError(relation)
-                "Tried to drop relation {}, but its type is null.".format(relation)
-            )
 
         self.cache_dropped(relation)
         self.execute_macro(DROP_RELATION_MACRO_NAME, kwargs={"relation": relation})
@@ -155,7 +152,7 @@ class SQLAdapter(BaseAdapter):
 
     def create_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaCreation(relation=_make_key(relation)))
+        fire_event(SchemaCreation(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }
@@ -166,7 +163,7 @@ class SQLAdapter(BaseAdapter):
 
     def drop_schema(self, relation: BaseRelation) -> None:
         relation = relation.without_identifier()
-        fire_event(SchemaDrop(relation=_make_key(relation)))
+        fire_event(SchemaDrop(relation=_make_ref_key_msg(relation)))
         kwargs = {
             "relation": relation,
         }

core/dbt/cli/main.py

@@ -31,7 +31,6 @@ def cli_runner():
 @p.cache_selected_only
 @p.debug
 @p.enable_legacy_logger
-@p.event_buffer_size
 @p.fail_fast
 @p.log_cache_events
 @p.log_format
@@ -47,6 +46,7 @@ def cli_runner():
 @p.version
 @p.version_check
 @p.warn_error
+@p.warn_error_options
 @p.write_json
 def cli(ctx, **kwargs):
     """An ELT tool for managing your SQL transformations and data models.

core/dbt/cli/option_types.py

@@ -1,6 +1,8 @@
 from click import ParamType
 import yaml
 
+from dbt.helper_types import WarnErrorOptions
+
 
 class YAML(ParamType):
     """The Click YAML type. Converts YAML strings into objects."""
@@ -17,6 +19,19 @@ class YAML(ParamType):
             self.fail(f"String '{value}' is not valid YAML", param, ctx)
 
 
+class WarnErrorOptionsType(YAML):
+    """The Click WarnErrorOptions type. Converts YAML strings into objects."""
+
+    name = "WarnErrorOptionsType"
+
+    def convert(self, value, param, ctx):
+        include_exclude = super().convert(value, param, ctx)
+
+        return WarnErrorOptions(
+            include=include_exclude.get("include", []), exclude=include_exclude.get("exclude", [])
+        )
+
+
 class Truthy(ParamType):
     """The Click Truthy type.  Converts strings into a "truthy" type"""
 

core/dbt/cli/params.py

@@ -1,7 +1,7 @@
 from pathlib import Path, PurePath
 
 import click
-from dbt.cli.option_types import YAML
+from dbt.cli.option_types import YAML, WarnErrorOptionsType
 from dbt.cli.resolvers import default_project_dir, default_profiles_dir
 
 
@@ -80,14 +80,6 @@ enable_legacy_logger = click.option(
     hidden=True,
 )
 
-event_buffer_size = click.option(
-    "--event-buffer-size",
-    envvar="DBT_EVENT_BUFFER_SIZE",
-    help="Sets the max number of events to buffer in EVENT_HISTORY.",
-    default=100000,
-    type=click.INT,
-)
-
 exclude = click.option("--exclude", envvar=None, help="Specify the nodes to exclude.")
 
 fail_fast = click.option(
@@ -278,7 +270,7 @@ show = click.option(
 )
 
 skip_profile_setup = click.option(
-    "--skip-profile-setup", "-s", envvar=None, help="Skip interative profile setup.", is_flag=True
+    "--skip-profile-setup", "-s", envvar=None, help="Skip interactive profile setup.", is_flag=True
 )
 
 # TODO:  The env var and name (reflected in flags) are corrections!
@@ -366,9 +358,20 @@ version_check = click.option(
 )
 
 warn_error = click.option(
-    "--warn-error/--no-warn-error",
+    "--warn-error",
     envvar="DBT_WARN_ERROR",
-    help="If dbt would normally warn, instead raise an exception. Examples include --models that selects nothing, deprecations, configurations with no associated models, invalid test configurations, and missing sources/refs in tests.",
+    help="If dbt would normally warn, instead raise an exception. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations, and missing sources/refs in tests.",
+    default=None,
+    flag_value=True,
+)
+
+warn_error_options = click.option(
+    "--warn-error-options",
+    envvar="DBT_WARN_ERROR_OPTIONS",
+    default=None,
+    help="""If dbt would normally warn, instead raise an exception based on include/exclude configuration. Examples include --select that selects nothing, deprecations, configurations with no associated models, invalid test configurations,
+    and missing sources/refs in tests. This argument should be a YAML string, with keys 'include' or 'exclude'. eg. '{"include": "all", "exclude": ["NoNodesForSelectionCriteria"]}'""",
+    type=WarnErrorOptionsType(),
 )
 
 write_json = click.option(

core/dbt/clients/_jinja_blocks.py

@@ -1,7 +1,15 @@
 import re
 from collections import namedtuple
 
-import dbt.exceptions
+from dbt.exceptions import (
+    BlockDefinitionNotAtTopError,
+    DbtInternalError,
+    MissingCloseTagError,
+    MissingControlFlowStartTagError,
+    NestedTagsError,
+    UnexpectedControlFlowEndTagError,
+    UnexpectedMacroEOFError,
+)
 
 
 def regex(pat):
@@ -139,10 +147,7 @@ class TagIterator:
     def _expect_match(self, expected_name, *patterns, **kwargs):
         match = self._first_match(*patterns, **kwargs)
         if match is None:
-            msg = 'unexpected EOF, expected {}, got "{}"'.format(
+            raise UnexpectedMacroEOFError(expected_name, self.data[self.pos :])
-                expected_name, self.data[self.pos :]
-            )
-            dbt.exceptions.raise_compiler_error(msg)
         return match
 
     def handle_expr(self, match):
@@ -256,7 +261,7 @@ class TagIterator:
             elif block_type_name is not None:
                 yield self.handle_tag(match)
             else:
-                raise dbt.exceptions.InternalException(
+                raise DbtInternalError(
                     "Invalid regex match in next_block, expected block start, "
                     "expr start, or comment start"
                 )
@@ -265,13 +270,6 @@ class TagIterator:
         return self.find_tags()
 
 
-duplicate_tags = (
-    "Got nested tags: {outer.block_type_name} (started at {outer.start}) did "
-    "not have a matching {{% end{outer.block_type_name} %}} before a "
-    "subsequent {inner.block_type_name} was found (started at {inner.start})"
-)
-
-
 _CONTROL_FLOW_TAGS = {
     "if": "endif",
     "for": "endfor",
@@ -319,33 +317,16 @@ class BlockIterator:
                     found = self.stack.pop()
                 else:
                     expected = _CONTROL_FLOW_END_TAGS[tag.block_type_name]
-                    dbt.exceptions.raise_compiler_error(
+                    raise UnexpectedControlFlowEndTagError(tag, expected, self.tag_parser)
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "never saw a preceeding {} (@ {})"
-                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
-                    )
                 expected = _CONTROL_FLOW_TAGS[found]
                 if expected != tag.block_type_name:
-                    dbt.exceptions.raise_compiler_error(
+                    raise MissingControlFlowStartTagError(tag, expected, self.tag_parser)
-                        (
-                            "Got an unexpected control flow end tag, got {} but "
-                            "expected {} next (@ {})"
-                        ).format(tag.block_type_name, expected, self.tag_parser.linepos(tag.start))
-                    )
 
             if tag.block_type_name in allowed_blocks:
                 if self.stack:
-                    dbt.exceptions.raise_compiler_error(
+                    raise BlockDefinitionNotAtTopError(self.tag_parser, tag.start)
-                        (
-                            "Got a block definition inside control flow at {}. "
-                            "All dbt block definitions must be at the top level"
-                        ).format(self.tag_parser.linepos(tag.start))
-                    )
                 if self.current is not None:
-                    dbt.exceptions.raise_compiler_error(
+                    raise NestedTagsError(outer=self.current, inner=tag)
-                        duplicate_tags.format(outer=self.current, inner=tag)
-                    )
                 if collect_raw_data:
                     raw_data = self.data[self.last_position : tag.start]
                     self.last_position = tag.start
@@ -366,11 +347,7 @@ class BlockIterator:
 
         if self.current:
             linecount = self.data[: self.current.end].count("\n") + 1
-            dbt.exceptions.raise_compiler_error(
+            raise MissingCloseTagError(self.current.block_type_name, linecount)
-                (
-                    "Reached EOF without finding a close tag for " "{} (searched from line {})"
-                ).format(self.current.block_type_name, linecount)
-            )
 
         if collect_raw_data:
             raw_data = self.data[self.last_position :]

core/dbt/clients/agate_helper.py

@@ -7,7 +7,7 @@ import json
 import dbt.utils
 from typing import Iterable, List, Dict, Union, Optional, Any
 
-from dbt.exceptions import RuntimeException
+from dbt.exceptions import DbtRuntimeError
 
 
 BOM = BOM_UTF8.decode("utf-8")  # '\ufeff'
@@ -168,7 +168,7 @@ class ColumnTypeBuilder(Dict[str, NullableAgateType]):
             return
         elif not isinstance(value, type(existing_type)):
             # actual type mismatch!
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"Tables contain columns with the same names ({key}), "
                 f"but different types ({value} vs {existing_type})"
             )

core/dbt/clients/git.py

@@ -14,10 +14,10 @@ from dbt.events.types import (
 )
 from dbt.exceptions import (
     CommandResultError,
-    RuntimeException,
+    GitCheckoutError,
-    bad_package_spec,
+    GitCloningError,
-    raise_git_cloning_error,
+    UnknownGitCloningProblemError,
-    raise_git_cloning_problem,
+    DbtRuntimeError,
 )
 from packaging import version
 
@@ -27,16 +27,6 @@ def _is_commit(revision: str) -> bool:
     return bool(re.match(r"\b[0-9a-f]{40}\b", revision))
 
 
-def _raise_git_cloning_error(repo, revision, error):
-    stderr = error.stderr.strip()
-    if "usage: git" in stderr:
-        stderr = stderr.split("\nusage: git")[0]
-    if re.match("fatal: destination path '(.+)' already exists", stderr):
-        raise_git_cloning_error(error)
-
-    bad_package_spec(repo, revision, stderr)
-
-
 def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirectory=None):
     has_revision = revision is not None
     is_commit = _is_commit(revision or "")
@@ -64,7 +54,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
     try:
         result = run_cmd(cwd, clone_cmd, env={"LC_ALL": "C"})
     except CommandResultError as exc:
-        _raise_git_cloning_error(repo, revision, exc)
+        raise GitCloningError(repo, revision, exc)
 
     if subdirectory:
         cwd_subdir = os.path.join(cwd, dirname or "")
@@ -72,7 +62,7 @@ def clone(repo, cwd, dirname=None, remove_git_dir=False, revision=None, subdirec
         try:
             run_cmd(cwd_subdir, clone_cmd_subdir)
         except CommandResultError as exc:
-            _raise_git_cloning_error(repo, revision, exc)
+            raise GitCloningError(repo, revision, exc)
 
     if remove_git_dir:
         rmdir(os.path.join(dirname, ".git"))
@@ -115,8 +105,7 @@ def checkout(cwd, repo, revision=None):
     try:
         return _checkout(cwd, repo, revision)
     except CommandResultError as exc:
-        stderr = exc.stderr.strip()
+        raise GitCheckoutError(repo=repo, revision=revision, error=exc)
-        bad_package_spec(repo, revision, stderr)
 
 
 def get_current_sha(cwd):
@@ -145,7 +134,7 @@ def clone_and_checkout(
         err = exc.stderr
         exists = re.match("fatal: destination path '(.+)' already exists", err)
         if not exists:
-            raise_git_cloning_problem(repo)
+            raise UnknownGitCloningProblemError(repo)
 
     directory = None
     start_sha = None
@@ -155,7 +144,7 @@ def clone_and_checkout(
     else:
         matches = re.match("Cloning into '(.+)'", err.decode("utf-8"))
         if matches is None:
-            raise RuntimeException(f'Error cloning {repo} - never saw "Cloning into ..." from git')
+            raise DbtRuntimeError(f'Error cloning {repo} - never saw "Cloning into ..." from git')
         directory = matches.group(1)
         fire_event(GitProgressPullingNewDependency(dir=directory))
     full_path = os.path.join(cwd, directory)

core/dbt/clients/jinja.py

@@ -25,17 +25,20 @@ from dbt.utils import (
 )
 
 from dbt.clients._jinja_blocks import BlockIterator, BlockData, BlockTag
-from dbt.contracts.graph.compiled import CompiledGenericTestNode
+from dbt.contracts.graph.nodes import GenericTestNode
-from dbt.contracts.graph.parsed import ParsedGenericTestNode
 
 from dbt.exceptions import (
-    InternalException,
+    CaughtMacroError,
-    raise_compiler_error,
+    CaughtMacroErrorWithNodeError,
-    CompilationException,
+    CompilationError,
-    invalid_materialization_argument,
+    DbtInternalError,
+    MaterializationArgError,
+    JinjaRenderingError,
     MacroReturn,
-    JinjaRenderingException,
+    MaterializtionMacroNotUsedError,
-    UndefinedMacroException,
+    NoSupportedLanguagesFoundError,
+    UndefinedCompilationError,
+    UndefinedMacroError,
 )
 from dbt import flags
 from dbt.node_types import ModelLanguage
@@ -158,9 +161,9 @@ def quoted_native_concat(nodes):
     except (ValueError, SyntaxError, MemoryError):
         result = raw
     if isinstance(raw, BoolMarker) and not isinstance(result, bool):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'bool'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'bool'")
     if isinstance(raw, NumberMarker) and not _is_number(result):
-        raise JinjaRenderingException(f"Could not convert value '{raw!s}' into type 'number'")
+        raise JinjaRenderingError(f"Could not convert value '{raw!s}' into type 'number'")
 
     return result
 
@@ -238,12 +241,12 @@ class BaseMacroGenerator:
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e))
+            raise CaughtMacroError(e)
 
     def call_macro(self, *args, **kwargs):
         # called from __call__ methods
         if self.context is None:
-            raise InternalException("Context is still None in call_macro!")
+            raise DbtInternalError("Context is still None in call_macro!")
         assert self.context is not None
 
         macro = self.get_macro()
@@ -270,7 +273,7 @@ class MacroStack(threading.local):
     def pop(self, name):
         got = self.call_stack.pop()
         if got != name:
-            raise InternalException(f"popped {got}, expected {name}")
+            raise DbtInternalError(f"popped {got}, expected {name}")
 
 
 class MacroGenerator(BaseMacroGenerator):
@@ -297,8 +300,8 @@ class MacroGenerator(BaseMacroGenerator):
         try:
             yield
         except (TypeError, jinja2.exceptions.TemplateRuntimeError) as e:
-            raise_compiler_error(str(e), self.macro)
+            raise CaughtMacroErrorWithNodeError(exc=e, node=self.macro)
-        except CompilationException as e:
+        except CompilationError as e:
             e.stack.append(self.macro)
             raise e
 
@@ -377,7 +380,7 @@ class MaterializationExtension(jinja2.ext.Extension):
                 node.defaults.append(languages)
 
             else:
-                invalid_materialization_argument(materialization_name, target.name)
+                raise MaterializationArgError(materialization_name, target.name)
 
         if SUPPORTED_LANG_ARG not in node.args:
             node.args.append(SUPPORTED_LANG_ARG)
@@ -452,7 +455,7 @@ def create_undefined(node=None):
             return self
 
         def __reduce__(self):
-            raise_compiler_error(f"{self.name} is undefined", node=node)
+            raise UndefinedCompilationError(name=self.name, node=node)
 
     return Undefined
 
@@ -510,10 +513,10 @@ def catch_jinja(node=None) -> Iterator[None]:
         yield
     except jinja2.exceptions.TemplateSyntaxError as e:
         e.translated = False
-        raise CompilationException(str(e), node) from e
+        raise CompilationError(str(e), node) from e
     except jinja2.exceptions.UndefinedError as e:
-        raise UndefinedMacroException(str(e), node) from e
+        raise UndefinedMacroError(str(e), node) from e
-    except CompilationException as exc:
+    except CompilationError as exc:
         exc.add_node(node)
         raise
 
@@ -620,7 +623,7 @@ GENERIC_TEST_KWARGS_NAME = "_dbt_generic_test_kwargs"
 
 def add_rendered_test_kwargs(
     context: Dict[str, Any],
-    node: Union[ParsedGenericTestNode, CompiledGenericTestNode],
+    node: GenericTestNode,
     capture_macros: bool = False,
 ) -> None:
     """Render each of the test kwargs in the given context using the native
@@ -652,13 +655,13 @@ def add_rendered_test_kwargs(
 
 def get_supported_languages(node: jinja2.nodes.Macro) -> List[ModelLanguage]:
     if "materialization" not in node.name:
-        raise_compiler_error("Only materialization macros can be used with this function")
+        raise MaterializtionMacroNotUsedError(node=node)
 
     no_kwargs = not node.defaults
     no_langs_found = SUPPORTED_LANG_ARG not in node.args
 
     if no_kwargs or no_langs_found:
-        raise_compiler_error(f"No supported_languages found in materialization macro {node.name}")
+        raise NoSupportedLanguagesFoundError(node=node)
 
     lang_idx = node.args.index(SUPPORTED_LANG_ARG)
     # indexing defaults from the end

core/dbt/clients/jinja_static.py

@@ -1,6 +1,6 @@
 import jinja2
 from dbt.clients.jinja import get_environment
-from dbt.exceptions import raise_compiler_error
+from dbt.exceptions import MacroNamespaceNotStringError, MacroNameNotStringError
 
 
 def statically_extract_macro_calls(string, ctx, db_wrapper=None):
@@ -117,20 +117,14 @@ def statically_parse_adapter_dispatch(func_call, ctx, db_wrapper):
                     func_name = kwarg.value.value
                     possible_macro_calls.append(func_name)
                 else:
-                    raise_compiler_error(
+                    raise MacroNameNotStringError(kwarg_value=kwarg.value.value)
-                        f"The macro_name parameter ({kwarg.value.value}) "
-                        "to adapter.dispatch was not a string"
-                    )
             elif kwarg.key == "macro_namespace":
                 # This will remain to enable static resolution
                 kwarg_type = type(kwarg.value).__name__
                 if kwarg_type == "Const":
                     macro_namespace = kwarg.value.value
                 else:
-                    raise_compiler_error(
+                    raise MacroNamespaceNotStringError(kwarg_type)
-                        "The macro_namespace parameter to adapter.dispatch "
-                        f"is a {kwarg_type}, not a string"
-                    )
 
     # positional arguments
     if packages_arg:

core/dbt/clients/registry.py

@@ -3,9 +3,9 @@ from typing import Any, Dict, List
 import requests
 from dbt.events.functions import fire_event
 from dbt.events.types import (
-    RegistryProgressMakingGETRequest,
+    RegistryProgressGETRequest,
     RegistryProgressGETResponse,
-    RegistryIndexProgressMakingGETRequest,
+    RegistryIndexProgressGETRequest,
     RegistryIndexProgressGETResponse,
     RegistryResponseUnexpectedType,
     RegistryResponseMissingTopKeys,
@@ -38,7 +38,7 @@ def _get_with_retries(package_name, registry_base_url=None):
 
 def _get(package_name, registry_base_url=None):
     url = _get_url(package_name, registry_base_url)
-    fire_event(RegistryProgressMakingGETRequest(url=url))
+    fire_event(RegistryProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryProgressGETResponse(url=url, resp_code=resp.status_code))
@@ -162,7 +162,7 @@ def get_compatible_versions(package_name, dbt_version, should_version_check) ->
 def _get_index(registry_base_url=None):
 
     url = _get_url("index", registry_base_url)
-    fire_event(RegistryIndexProgressMakingGETRequest(url=url))
+    fire_event(RegistryIndexProgressGETRequest(url=url))
     # all exceptions from requests get caught in the retry logic so no need to wrap this here
     resp = requests.get(url, timeout=30)
     fire_event(RegistryIndexProgressGETResponse(url=url, resp_code=resp.status_code))

core/dbt/clients/system.py

@@ -19,8 +19,8 @@ from dbt.events.types import (
     SystemErrorRetrievingModTime,
     SystemCouldNotWrite,
     SystemExecutingCmd,
-    SystemStdOutMsg,
+    SystemStdOut,
-    SystemStdErrMsg,
+    SystemStdErr,
     SystemReportReturnCode,
 )
 import dbt.exceptions
@@ -144,7 +144,8 @@ def make_symlink(source: str, link_path: str) -> None:
     Create a symlink at `link_path` referring to `source`.
     """
     if not supports_symlinks():
-        dbt.exceptions.system_error("create a symbolic link")
+        # TODO: why not import these at top?
+        raise dbt.exceptions.SymbolicLinkError()
 
     os.symlink(source, link_path)
 
@@ -411,7 +412,7 @@ def _interpret_oserror(exc: OSError, cwd: str, cmd: List[str]) -> NoReturn:
         _handle_posix_error(exc, cwd, cmd)
 
     # this should not be reachable, raise _something_ at least!
-    raise dbt.exceptions.InternalException(
+    raise dbt.exceptions.DbtInternalError(
         "Unhandled exception in _interpret_oserror: {}".format(exc)
     )
 
@@ -440,8 +441,8 @@ def run_cmd(cwd: str, cmd: List[str], env: Optional[Dict[str, Any]] = None) -> T
     except OSError as exc:
         _interpret_oserror(exc, cwd, cmd)
 
-    fire_event(SystemStdOutMsg(bmsg=out))
+    fire_event(SystemStdOut(bmsg=out))
-    fire_event(SystemStdErrMsg(bmsg=err))
+    fire_event(SystemStdErr(bmsg=err))
 
     if proc.returncode != 0:
         fire_event(SystemReportReturnCode(returncode=proc.returncode))

core/dbt/clients/yaml_helper.py

@@ -60,4 +60,4 @@ def load_yaml_text(contents, path=None):
         else:
             error = str(e)
 
-        raise dbt.exceptions.ValidationException(error)
+        raise dbt.exceptions.DbtValidationError(error)

core/dbt/compilation.py

@@ -1,6 +1,6 @@
 import os
 from collections import defaultdict
-from typing import List, Dict, Any, Tuple, cast, Optional
+from typing import List, Dict, Any, Tuple, Optional
 
 import networkx as nx  # type: ignore
 import pickle
@@ -12,23 +12,23 @@ from dbt.clients import jinja
 from dbt.clients.system import make_directory
 from dbt.context.providers import generate_runtime_model_context
 from dbt.contracts.graph.manifest import Manifest, UniqueID
-from dbt.contracts.graph.compiled import (
+from dbt.contracts.graph.nodes import (
-    COMPILED_TYPES,
+    ManifestNode,
-    CompiledGenericTestNode,
+    ManifestSQLNode,
+    GenericTestNode,
     GraphMemberNode,
     InjectedCTE,
-    ManifestNode,
+    SeedNode,
-    NonSourceCompiledNode,
 )
-from dbt.contracts.graph.parsed import ParsedNode
 from dbt.exceptions import (
-    dependency_not_found,
+    GraphDependencyNotFoundError,
-    InternalException,
+    DbtInternalError,
-    RuntimeException,
+    DbtRuntimeError,
 )
 from dbt.graph import Graph
 from dbt.events.functions import fire_event
-from dbt.events.types import FoundStats, CompilingNode, WritingInjectedSQLForNode
+from dbt.events.types import FoundStats, WritingInjectedSQLForNode
+from dbt.events.contextvars import get_node_info
 from dbt.node_types import NodeType, ModelLanguage
 from dbt.events.format import pluralize
 import dbt.tracking
@@ -36,14 +36,6 @@ import dbt.tracking
 graph_file_name = "graph.gpickle"
 
 
-def _compiled_type_for(model: ParsedNode):
-    if type(model) not in COMPILED_TYPES:
-        raise InternalException(
-            f"Asked to compile {type(model)} node, but it has no compiled form"
-        )
-    return COMPILED_TYPES[type(model)]
-
-
 def print_compile_stats(stats):
     names = {
         NodeType.Model: "model",
@@ -56,6 +48,7 @@ def print_compile_stats(stats):
         NodeType.Source: "source",
         NodeType.Exposure: "exposure",
         NodeType.Metric: "metric",
+        NodeType.Entity: "entity",
     }
 
     results = {k: 0 for k in names.keys()}
@@ -91,6 +84,8 @@ def _generate_stats(manifest: Manifest):
         stats[exposure.resource_type] += 1
     for metric in manifest.metrics.values():
         stats[metric.resource_type] += 1
+    for entity in manifest.entities.values():
+        stats[entity.resource_type] += 1
     for macro in manifest.macros.values():
         stats[macro.resource_type] += 1
     return stats
@@ -176,7 +171,7 @@ class Compiler:
     # a dict for jinja rendering of SQL
     def _create_node_context(
         self,
-        node: NonSourceCompiledNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
@@ -184,7 +179,7 @@ class Compiler:
         context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
 
-        if isinstance(node, CompiledGenericTestNode):
+        if isinstance(node, GenericTestNode):
             # for test nodes, add a special keyword args value to the context
             jinja.add_rendered_test_kwargs(context, node)
 
@@ -195,14 +190,6 @@ class Compiler:
         relation_cls = adapter.Relation
         return relation_cls.add_ephemeral_prefix(name)
 
-    def _get_relation_name(self, node: ParsedNode):
-        relation_name = None
-        if node.is_relational and not node.is_ephemeral_model:
-            adapter = get_adapter(self.config)
-            relation_cls = adapter.Relation
-            relation_name = str(relation_cls.create_from(self.config, node))
-        return relation_name
-
     def _inject_ctes_into_sql(self, sql: str, ctes: List[InjectedCTE]) -> str:
         """
         `ctes` is a list of InjectedCTEs like:
@@ -261,10 +248,10 @@ class Compiler:
 
     def _recursively_prepend_ctes(
         self,
-        model: NonSourceCompiledNode,
+        model: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]],
-    ) -> Tuple[NonSourceCompiledNode, List[InjectedCTE]]:
+    ) -> Tuple[ManifestSQLNode, List[InjectedCTE]]:
         """This method is called by the 'compile_node' method. Starting
         from the node that it is passed in, it will recursively call
         itself using the 'extra_ctes'.  The 'ephemeral' models do
@@ -273,13 +260,14 @@ class Compiler:
         inserting CTEs into the SQL.
         """
         if model.compiled_code is None:
-            raise RuntimeException("Cannot inject ctes into an unparsed node", model)
+            raise DbtRuntimeError("Cannot inject ctes into an unparsed node", model)
         if model.extra_ctes_injected:
             return (model, model.extra_ctes)
 
         # Just to make it plain that nothing is actually injected for this case
         if not model.extra_ctes:
-            model.extra_ctes_injected = True
+            if not isinstance(model, SeedNode):
+                model.extra_ctes_injected = True
             manifest.update_node(model)
             return (model, model.extra_ctes)
 
@@ -293,20 +281,19 @@ class Compiler:
         # ephemeral model.
         for cte in model.extra_ctes:
             if cte.id not in manifest.nodes:
-                raise InternalException(
+                raise DbtInternalError(
                     f"During compilation, found a cte reference that "
                     f"could not be resolved: {cte.id}"
                 )
             cte_model = manifest.nodes[cte.id]
+            assert not isinstance(cte_model, SeedNode)
 
             if not cte_model.is_ephemeral_model:
-                raise InternalException(f"{cte.id} is not ephemeral")
+                raise DbtInternalError(f"{cte.id} is not ephemeral")
 
             # This model has already been compiled, so it's been
             # through here before
             if getattr(cte_model, "compiled", False):
-                assert isinstance(cte_model, tuple(COMPILED_TYPES.values()))
-                cte_model = cast(NonSourceCompiledNode, cte_model)
                 new_prepended_ctes = cte_model.extra_ctes
 
             # if the cte_model isn't compiled, i.e. first time here
@@ -343,21 +330,19 @@ class Compiler:
 
         return model, prepended_ctes
 
-    # creates a compiled_node from the ManifestNode passed in,
+    # Sets compiled fields in the ManifestSQLNode passed in,
     # creates a "context" dictionary for jinja rendering,
     # and then renders the "compiled_code" using the node, the
     # raw_code and the context.
     def _compile_node(
         self,
-        node: ManifestNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         if extra_context is None:
             extra_context = {}
 
-        fire_event(CompilingNode(unique_id=node.unique_id))
-
         data = node.to_dict(omit_none=True)
         data.update(
             {
@@ -367,9 +352,8 @@ class Compiler:
                 "extra_ctes": [],
             }
         )
-        compiled_node = _compiled_type_for(node).from_dict(data)
 
-        if compiled_node.language == ModelLanguage.python:
+        if node.language == ModelLanguage.python:
             # TODO could we also 'minify' this code at all? just aesthetic, not functional
 
             # quoating seems like something very specific to sql so far
@@ -377,7 +361,7 @@ class Compiler:
             # TODO try to find better way to do this, given that
             original_quoting = self.config.quoting
             self.config.quoting = {key: False for key in original_quoting.keys()}
-            context = self._create_node_context(compiled_node, manifest, extra_context)
+            context = self._create_node_context(node, manifest, extra_context)
 
             postfix = jinja.get_rendered(
                 "{{ py_script_postfix(model) }}",
@@ -385,23 +369,21 @@ class Compiler:
                 node,
             )
             # we should NOT jinja render the python model's 'raw code'
-            compiled_node.compiled_code = f"{node.raw_code}\n\n{postfix}"
+            node.compiled_code = f"{node.raw_code}\n\n{postfix}"
             # restore quoting settings in the end since context is lazy evaluated
             self.config.quoting = original_quoting
 
         else:
-            context = self._create_node_context(compiled_node, manifest, extra_context)
+            context = self._create_node_context(node, manifest, extra_context)
-            compiled_node.compiled_code = jinja.get_rendered(
+            node.compiled_code = jinja.get_rendered(
                 node.raw_code,
                 context,
                 node,
             )
 
-        compiled_node.relation_name = self._get_relation_name(node)
+        node.compiled = True
 
-        compiled_node.compiled = True
+        return node
-
-        return compiled_node
 
     def write_graph_file(self, linker: Linker, manifest: Manifest):
         filename = graph_file_name
@@ -419,8 +401,10 @@ class Compiler:
                 linker.dependency(node.unique_id, (manifest.sources[dependency].unique_id))
             elif dependency in manifest.metrics:
                 linker.dependency(node.unique_id, (manifest.metrics[dependency].unique_id))
+            elif dependency in manifest.entities:
+                linker.dependency(node.unique_id, (manifest.entities[dependency].unique_id))
             else:
-                dependency_not_found(node, dependency)
+                raise GraphDependencyNotFoundError(node, dependency)
 
     def link_graph(self, linker: Linker, manifest: Manifest, add_test_edges: bool = False):
         for source in manifest.sources.values():
@@ -431,6 +415,8 @@ class Compiler:
             self.link_node(linker, exposure, manifest)
         for metric in manifest.metrics.values():
             self.link_node(linker, metric, manifest)
+        for entity in manifest.entities.values():
+            self.link_node(linker, entity, manifest)
 
         cycle = linker.find_cycles()
 
@@ -508,10 +494,13 @@ class Compiler:
         return Graph(linker.graph)
 
     # writes the "compiled_code" into the target/compiled directory
-    def _write_node(self, node: NonSourceCompiledNode) -> ManifestNode:
+    def _write_node(self, node: ManifestSQLNode) -> ManifestSQLNode:
-        if not node.extra_ctes_injected or node.resource_type == NodeType.Snapshot:
+        if not node.extra_ctes_injected or node.resource_type in (
+            NodeType.Snapshot,
+            NodeType.Seed,
+        ):
             return node
-        fire_event(WritingInjectedSQLForNode(unique_id=node.unique_id))
+        fire_event(WritingInjectedSQLForNode(node_info=get_node_info()))
 
         if node.compiled_code:
             node.compiled_path = node.write_node(
@@ -521,11 +510,11 @@ class Compiler:
 
     def compile_node(
         self,
-        node: ManifestNode,
+        node: ManifestSQLNode,
         manifest: Manifest,
         extra_context: Optional[Dict[str, Any]] = None,
         write: bool = True,
-    ) -> NonSourceCompiledNode:
+    ) -> ManifestSQLNode:
         """This is the main entry point into this code. It's called by
         CompileRunner.compile, GenericRPCRunner.compile, and
         RunTask.get_hook_sql. It calls '_compile_node' to convert

core/dbt/config/profile.py

@@ -9,12 +9,14 @@ from dbt.clients.system import load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import Credentials, HasCredentials
 from dbt.contracts.project import ProfileConfig, UserConfig
-from dbt.exceptions import CompilationException
+from dbt.exceptions import (
-from dbt.exceptions import DbtProfileError
+    CompilationError,
-from dbt.exceptions import DbtProjectError
+    DbtProfileError,
-from dbt.exceptions import ValidationException
+    DbtProjectError,
-from dbt.exceptions import RuntimeException
+    DbtValidationError,
-from dbt.exceptions import validator_error_message
+    DbtRuntimeError,
+    ProfileConfigError,
+)
 from dbt.events.types import MissingProfileTarget
 from dbt.events.functions import fire_event
 from dbt.utils import coerce_dict_str
@@ -58,9 +60,9 @@ def read_profile(profiles_dir: str) -> Dict[str, Any]:
                 msg = f"The profiles.yml file at {path} is empty"
                 raise DbtProfileError(INVALID_PROFILE_MESSAGE.format(error_string=msg))
             return yaml_content
-        except ValidationException as e:
+        except DbtValidationError as e:
             msg = INVALID_PROFILE_MESSAGE.format(error_string=e)
-            raise ValidationException(msg) from e
+            raise DbtValidationError(msg) from e
 
     return {}
 
@@ -73,7 +75,7 @@ def read_user_config(directory: str) -> UserConfig:
             if user_config is not None:
                 UserConfig.validate(user_config)
                 return UserConfig.from_dict(user_config)
-    except (RuntimeException, ValidationError):
+    except (DbtRuntimeError, ValidationError):
         pass
     return UserConfig()
 
@@ -156,7 +158,7 @@ class Profile(HasCredentials):
             dct = self.to_profile_info(serialize_credentials=True)
             ProfileConfig.validate(dct)
         except ValidationError as exc:
-            raise DbtProfileError(validator_error_message(exc)) from exc
+            raise ProfileConfigError(exc) from exc
 
     @staticmethod
     def _credentials_from_profile(
@@ -180,8 +182,8 @@ class Profile(HasCredentials):
             data = cls.translate_aliases(profile)
             cls.validate(data)
             credentials = cls.from_dict(data)
-        except (RuntimeException, ValidationError) as e:
+        except (DbtRuntimeError, ValidationError) as e:
-            msg = str(e) if isinstance(e, RuntimeException) else e.message
+            msg = str(e) if isinstance(e, DbtRuntimeError) else e.message
             raise DbtProfileError(
                 'Credentials in profile "{}", target "{}" invalid: {}'.format(
                     profile_name, target_name, msg
@@ -297,7 +299,7 @@ class Profile(HasCredentials):
 
         try:
             profile_data = renderer.render_data(raw_profile_data)
-        except CompilationException as exc:
+        except CompilationError as exc:
             raise DbtProfileError(str(exc)) from exc
         return target_name, profile_data
 

core/dbt/config/project.py

@@ -16,19 +16,19 @@ import hashlib
 import os
 
 from dbt import flags, deprecations
-from dbt.clients.system import resolve_path_from_base
+from dbt.clients.system import path_exists, resolve_path_from_base, load_file_contents
-from dbt.clients.system import path_exists
-from dbt.clients.system import load_file_contents
 from dbt.clients.yaml_helper import load_yaml_text
 from dbt.contracts.connection import QueryComment
-from dbt.exceptions import DbtProjectError
+from dbt.exceptions import (
-from dbt.exceptions import SemverException
+    DbtProjectError,
-from dbt.exceptions import validator_error_message
+    SemverError,
-from dbt.exceptions import RuntimeException
+    ProjectContractBrokenError,
+    ProjectContractError,
+    DbtRuntimeError,
+)
 from dbt.graph import SelectionSpec
 from dbt.helper_types import NoValue
-from dbt.semver import VersionSpecifier
+from dbt.semver import VersionSpecifier, versions_compatible
-from dbt.semver import versions_compatible
 from dbt.version import get_installed_version
 from dbt.utils import MultiDict
 from dbt.node_types import NodeType
@@ -219,7 +219,7 @@ def _get_required_version(
 
     try:
         dbt_version = _parse_versions(dbt_raw_version)
-    except SemverException as e:
+    except SemverError as e:
         raise DbtProjectError(str(e)) from e
 
     if verify_version:
@@ -248,7 +248,7 @@ class PartialProject(RenderComponents):
     project_name: Optional[str] = field(
         metadata=dict(
             description=(
-                "The name of the project. This should always be set and will not " "be rendered"
+                "The name of the project. This should always be set and will not be rendered"
             )
         )
     )
@@ -325,7 +325,7 @@ class PartialProject(RenderComponents):
             ProjectContract.validate(rendered.project_dict)
             cfg = ProjectContract.from_dict(rendered.project_dict)
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ProjectContractError(e) from e
         # name/version are required in the Project definition, so we can assume
         # they are present
         name = cfg.name
@@ -381,6 +381,7 @@ class PartialProject(RenderComponents):
         sources: Dict[str, Any]
         tests: Dict[str, Any]
         metrics: Dict[str, Any]
+        entities: Dict[str, Any]
         exposures: Dict[str, Any]
         vars_value: VarProvider
 
@@ -391,6 +392,7 @@ class PartialProject(RenderComponents):
         sources = cfg.sources
         tests = cfg.tests
         metrics = cfg.metrics
+        entities = cfg.entities
         exposures = cfg.exposures
         if cfg.vars is None:
             vars_dict: Dict[str, Any] = {}
@@ -446,6 +448,7 @@ class PartialProject(RenderComponents):
             sources=sources,
             tests=tests,
             metrics=metrics,
+            entities=entities,
             exposures=exposures,
             vars=vars_value,
             config_version=cfg.config_version,
@@ -550,6 +553,7 @@ class Project:
     sources: Dict[str, Any]
     tests: Dict[str, Any]
     metrics: Dict[str, Any]
+    entities: Dict[str, Any]
     exposures: Dict[str, Any]
     vars: VarProvider
     dbt_version: List[VersionSpecifier]
@@ -624,6 +628,7 @@ class Project:
                 "sources": self.sources,
                 "tests": self.tests,
                 "metrics": self.metrics,
+                "entities": self.entities,
                 "exposures": self.exposures,
                 "vars": self.vars.to_dict(),
                 "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
@@ -642,7 +647,7 @@ class Project:
         try:
             ProjectContract.validate(self.to_project_config())
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ProjectContractBrokenError(e) from e
 
     @classmethod
     def partial_load(cls, project_root: str, *, verify_version: bool = False) -> PartialProject:
@@ -667,8 +672,8 @@ class Project:
 
     def get_selector(self, name: str) -> Union[SelectionSpec, bool]:
         if name not in self.selectors:
-            raise RuntimeException(
+            raise DbtRuntimeError(
-                f"Could not find selector named {name}, expected one of " f"{list(self.selectors)}"
+                f"Could not find selector named {name}, expected one of {list(self.selectors)}"
             )
         return self.selectors[name]["definition"]
 

core/dbt/config/renderer.py

@@ -8,7 +8,7 @@ from dbt.context.target import TargetContext
 from dbt.context.secret import SecretContext, SECRET_PLACEHOLDER
 from dbt.context.base import BaseContext
 from dbt.contracts.connection import HasCredentials
-from dbt.exceptions import DbtProjectError, CompilationException, RecursionException
+from dbt.exceptions import DbtProjectError, CompilationError, RecursionError
 from dbt.utils import deep_map_render
 
 
@@ -40,14 +40,14 @@ class BaseRenderer:
         try:
             with catch_jinja():
                 return get_rendered(value, self.context, native=True)
-        except CompilationException as exc:
+        except CompilationError as exc:
             msg = f"Could not render {value}: {exc.msg}"
-            raise CompilationException(msg) from exc
+            raise CompilationError(msg) from exc
 
     def render_data(self, data: Dict[str, Any]) -> Dict[str, Any]:
         try:
             return deep_map_render(self.render_entry, data)
-        except RecursionException:
+        except RecursionError:
             raise DbtProjectError(
                 f"Cycle detected: {self.name} input has a reference to itself", project=data
             )
@@ -159,7 +159,8 @@ class DbtProjectYamlRenderer(BaseRenderer):
         if first in {"seeds", "models", "snapshots", "tests"}:
             keypath_parts = {(k.lstrip("+ ") if isinstance(k, str) else k) for k in keypath}
             # model-level hooks
-            if "pre-hook" in keypath_parts or "post-hook" in keypath_parts:
+            late_rendered_hooks = {"pre-hook", "post-hook", "pre_hook", "post_hook"}
+            if keypath_parts.intersection(late_rendered_hooks):
                 return False
 
         return True

core/dbt/config/runtime.py

@@ -3,31 +3,42 @@ import os
 from copy import deepcopy
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Dict, Any, Optional, Mapping, Iterator, Iterable, Tuple, List, MutableSet, Type
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    Iterator,
+    Mapping,
+    MutableSet,
+    Optional,
+    Tuple,
+    Type,
+    Union,
+)
 
-from .profile import Profile
-from .project import Project
-from .renderer import DbtProjectYamlRenderer, ProfileRenderer
-from .utils import parse_cli_vars
 from dbt import flags
-from dbt.adapters.factory import get_relation_class_by_name, get_include_paths
+from dbt.adapters.factory import get_include_paths, get_relation_class_by_name
-from dbt.helper_types import FQNPath, PathSet, DictDefaultEmptyStr
 from dbt.config.profile import read_user_config
 from dbt.contracts.connection import AdapterRequiredConfig, Credentials
 from dbt.contracts.graph.manifest import ManifestMetadata
-from dbt.contracts.relation import ComponentName
-from dbt.ui import warning_tag
-
 from dbt.contracts.project import Configuration, UserConfig
-from dbt.exceptions import (
+from dbt.contracts.relation import ComponentName
-    RuntimeException,
-    DbtProjectError,
-    validator_error_message,
-    warn_or_error,
-    raise_compiler_error,
-)
-
 from dbt.dataclass_schema import ValidationError
+from dbt.exceptions import (
+    ConfigContractBrokenError,
+    DbtProjectError,
+    NonUniquePackageNameError,
+    DbtRuntimeError,
+    UninstalledPackagesFoundError,
+)
+from dbt.events.functions import warn_or_error
+from dbt.events.types import UnusedResourceConfigPath
+from dbt.helper_types import DictDefaultEmptyStr, FQNPath, PathSet
+
+from .profile import Profile
+from .project import Project, PartialProject
+from .renderer import DbtProjectYamlRenderer, ProfileRenderer
+from .utils import parse_cli_vars
 
 
 def _project_quoting_dict(proj: Project, profile: Profile) -> Dict[ComponentName, bool]:
@@ -106,6 +117,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             sources=project.sources,
             tests=project.tests,
             metrics=project.metrics,
+            entities=project.entities,
             exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
@@ -176,7 +188,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         try:
             Configuration.validate(self.serialize())
         except ValidationError as e:
-            raise DbtProjectError(validator_error_message(e)) from e
+            raise ConfigContractBrokenError(e) from e
 
     @classmethod
     def _get_rendered_profile(
@@ -190,28 +202,52 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
     @classmethod
     def collect_parts(cls: Type["RuntimeConfig"], args: Any) -> Tuple[Project, Profile]:
-        # profile_name from the project
-        project_root = args.project_dir if args.project_dir else os.getcwd()
-        version_check = bool(flags.VERSION_CHECK)
-        partial = Project.partial_load(project_root, verify_version=version_check)
 
-        # build the profile using the base renderer and the one fact we know
+        cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
-        # Note: only the named profile section is rendered. The rest of the
+
-        # profile is ignored.
+        profile = cls.collect_profile(args=args)
+        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
+        project = cls.collect_project(args=args, project_renderer=project_renderer)
+        assert type(project) is Project
+        return (project, profile)
+
+    @classmethod
+    def collect_profile(
+        cls: Type["RuntimeConfig"], args: Any, profile_name: Optional[str] = None
+    ) -> Profile:
+
         cli_vars: Dict[str, Any] = parse_cli_vars(getattr(args, "vars", "{}"))
         profile_renderer = ProfileRenderer(cli_vars)
-        profile_name = partial.render_profile_name(profile_renderer)
+
+        # build the profile using the base renderer and the one fact we know
+        if profile_name is None:
+            # Note: only the named profile section is rendered here. The rest of the
+            # profile is ignored.
+            partial = cls.collect_project(args)
+            assert type(partial) is PartialProject
+            profile_name = partial.render_profile_name(profile_renderer)
+
         profile = cls._get_rendered_profile(args, profile_renderer, profile_name)
         # Save env_vars encountered in rendering for partial parsing
         profile.profile_env_vars = profile_renderer.ctx_obj.env_vars
+        return profile
 
-        # get a new renderer using our target information and render the
+    @classmethod
-        # project
+    def collect_project(
-        project_renderer = DbtProjectYamlRenderer(profile, cli_vars)
+        cls: Type["RuntimeConfig"],
-        project = partial.render(project_renderer)
+        args: Any,
-        # Save env_vars encountered in rendering for partial parsing
+        project_renderer: Optional[DbtProjectYamlRenderer] = None,
-        project.project_env_vars = project_renderer.ctx_obj.env_vars
+    ) -> Union[Project, PartialProject]:
-        return (project, profile)
+
+        project_root = args.project_dir if args.project_dir else os.getcwd()
+        version_check = bool(flags.VERSION_CHECK)
+        partial = Project.partial_load(project_root, verify_version=version_check)
+        if project_renderer is None:
+            return partial
+        else:
+            project = partial.render(project_renderer)
+            project.project_env_vars = project_renderer.ctx_obj.env_vars
+            return project
 
     # Called in main.py, lib.py, task/base.py
     @classmethod
@@ -223,7 +259,7 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
         :param args: The arguments as parsed from the cli.
         :raises DbtProjectError: If the project is invalid or missing.
         :raises DbtProfileError: If the profile is invalid or missing.
-        :raises ValidationException: If the cli variables are invalid.
+        :raises DbtValidationError: If the cli variables are invalid.
         """
         project, profile = cls.collect_parts(args)
 
@@ -277,14 +313,15 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
             "sources": self._get_config_paths(self.sources),
             "tests": self._get_config_paths(self.tests),
             "metrics": self._get_config_paths(self.metrics),
+            "entities": self._get_config_paths(self.entities),
             "exposures": self._get_config_paths(self.exposures),
         }
 
-    def get_unused_resource_config_paths(
+    def warn_for_unused_resource_config_paths(
         self,
         resource_fqns: Mapping[str, PathSet],
         disabled: PathSet,
-    ) -> List[FQNPath]:
+    ) -> None:
         """Return a list of lists of strings, where each inner list of strings
         represents a type + FQN path of a resource configuration that is not
         used.
@@ -298,23 +335,13 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
 
             for config_path in config_paths:
                 if not _is_config_used(config_path, fqns):
-                    unused_resource_config_paths.append((resource_type,) + config_path)
+                    resource_path = ".".join(i for i in ((resource_type,) + config_path))
-        return unused_resource_config_paths
+                    unused_resource_config_paths.append(resource_path)
 
-    def warn_for_unused_resource_config_paths(
+        if len(unused_resource_config_paths) == 0:
-        self,
-        resource_fqns: Mapping[str, PathSet],
-        disabled: PathSet,
-    ) -> None:
-        unused = self.get_unused_resource_config_paths(resource_fqns, disabled)
-        if len(unused) == 0:
             return
 
-        msg = UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE.format(
+        warn_or_error(UnusedResourceConfigPath(unused_config_paths=unused_resource_config_paths))
-            len(unused), "\n".join("- {}".format(".".join(u)) for u in unused)
-        )
-
-        warn_or_error(msg, log_fmt=warning_tag("{}"))
 
     def load_dependencies(self, base_only=False) -> Mapping[str, "RuntimeConfig"]:
         if self.dependencies is None:
@@ -328,22 +355,15 @@ class RuntimeConfig(Project, Profile, AdapterRequiredConfig):
                 count_packages_specified = len(self.packages.packages)  # type: ignore
                 count_packages_installed = len(tuple(self._get_project_directories()))
                 if count_packages_specified > count_packages_installed:
-                    raise_compiler_error(
+                    raise UninstalledPackagesFoundError(
-                        f"dbt found {count_packages_specified} package(s) "
+                        count_packages_specified,
-                        f"specified in packages.yml, but only "
+                        count_packages_installed,
-                        f"{count_packages_installed} package(s) installed "
+                        self.packages_install_path,
-                        f'in {self.packages_install_path}. Run "dbt deps" to '
-                        f"install package dependencies."
                     )
                 project_paths = itertools.chain(internal_packages, self._get_project_directories())
             for project_name, project in self.load_projects(project_paths):
                 if project_name in all_projects:
-                    raise_compiler_error(
+                    raise NonUniquePackageNameError(project_name)
-                        f"dbt found more than one package with the name "
-                        f'"{project_name}" included in this project. Package '
-                        f"names must be unique in a project. Please rename "
-                        f"one of these packages."
-                    )
                 all_projects[project_name] = project
             self.dependencies = all_projects
         return self.dependencies
@@ -408,7 +428,7 @@ class UnsetProfile(Profile):
 
     def __getattribute__(self, name):
         if name in {"profile_name", "target_name", "threads"}:
-            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
+            raise DbtRuntimeError(f'Error: disallowed attribute "{name}" - no profile!')
 
         return Profile.__getattribute__(self, name)
 
@@ -435,7 +455,7 @@ class UnsetProfileConfig(RuntimeConfig):
     def __getattribute__(self, name):
         # Override __getattribute__ to check that the attribute isn't 'banned'.
         if name in {"profile_name", "target_name"}:
-            raise RuntimeException(f'Error: disallowed attribute "{name}" - no profile!')
+            raise DbtRuntimeError(f'Error: disallowed attribute "{name}" - no profile!')
 
         # avoid every attribute access triggering infinite recursion
         return RuntimeConfig.__getattribute__(self, name)
@@ -482,6 +502,7 @@ class UnsetProfileConfig(RuntimeConfig):
                 "sources": self.sources,
                 "tests": self.tests,
                 "metrics": self.metrics,
+                "entities": self.entities,
                 "exposures": self.exposures,
                 "vars": self.vars.to_dict(),
                 "require-dbt-version": [v.to_version_string() for v in self.dbt_version],
@@ -544,6 +565,7 @@ class UnsetProfileConfig(RuntimeConfig):
             sources=project.sources,
             tests=project.tests,
             metrics=project.metrics,
+            entities=project.entities,
             exposures=project.exposures,
             vars=project.vars,
             config_version=project.config_version,
@@ -584,21 +606,13 @@ class UnsetProfileConfig(RuntimeConfig):
         :param args: The arguments as parsed from the cli.
         :raises DbtProjectError: If the project is invalid or missing.
         :raises DbtProfileError: If the profile is invalid or missing.
-        :raises ValidationException: If the cli variables are invalid.
+        :raises DbtValidationError: If the cli variables are invalid.
         """
         project, profile = cls.collect_parts(args)
 
         return cls.from_parts(project=project, profile=profile, args=args)
 
 
-UNUSED_RESOURCE_CONFIGURATION_PATH_MESSAGE = """\
-Configuration paths exist in your dbt_project.yml file which do not \
-apply to any resources.
-There are {} unused configuration paths:
-{}
-"""
-
-
 def _is_config_used(path, fqns):
     if fqns:
         for fqn in fqns:

core/dbt/config/selectors.py

@@ -12,7 +12,7 @@ from dbt.clients.system import (
     resolve_path_from_base,
 )
 from dbt.contracts.selection import SelectorFile
-from dbt.exceptions import DbtSelectorsError, RuntimeException
+from dbt.exceptions import DbtSelectorsError, DbtRuntimeError
 from dbt.graph import parse_from_selectors_definition, SelectionSpec
 from dbt.graph.selector_spec import SelectionCriteria
 
@@ -46,7 +46,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
                 f"yaml-selectors",
                 result_type="invalid_selector",
             ) from exc
-        except RuntimeException as exc:
+        except DbtRuntimeError as exc:
             raise DbtSelectorsError(
                 f"Could not read selector file data: {exc}",
                 result_type="invalid_selector",
@@ -62,7 +62,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
     ) -> "SelectorConfig":
         try:
             rendered = renderer.render_data(data)
-        except (ValidationError, RuntimeException) as exc:
+        except (ValidationError, DbtRuntimeError) as exc:
             raise DbtSelectorsError(
                 f"Could not render selector data: {exc}",
                 result_type="invalid_selector",
@@ -77,7 +77,7 @@ class SelectorConfig(Dict[str, Dict[str, Union[SelectionSpec, bool]]]):
     ) -> "SelectorConfig":
         try:
             data = load_yaml_text(load_file_contents(str(path)))
-        except (ValidationError, RuntimeException) as exc:
+        except (ValidationError, DbtRuntimeError) as exc:
             raise DbtSelectorsError(
                 f"Could not read selector file: {exc}",
                 result_type="invalid_selector",

core/dbt/config/utils.py

@@ -8,24 +8,24 @@ from dbt.clients import yaml_helper
 from dbt.config import Profile, Project, read_user_config
 from dbt.config.renderer import DbtProjectYamlRenderer, ProfileRenderer
 from dbt.events.functions import fire_event
-from dbt.events.types import InvalidVarsYAML
+from dbt.events.types import InvalidOptionYAML
-from dbt.exceptions import ValidationException, raise_compiler_error
+from dbt.exceptions import DbtValidationError, OptionNotYamlDictError
 
 
 def parse_cli_vars(var_string: str) -> Dict[str, Any]:
+    return parse_cli_yaml_string(var_string, "vars")
+
+
+def parse_cli_yaml_string(var_string: str, cli_option_name: str) -> Dict[str, Any]:
     try:
         cli_vars = yaml_helper.load_yaml_text(var_string)
         var_type = type(cli_vars)
         if var_type is dict:
             return cli_vars
         else:
-            type_name = var_type.__name__
+            raise OptionNotYamlDictError(var_type, cli_option_name)
-            raise_compiler_error(
+    except DbtValidationError:
-                "The --vars argument must be a YAML dictionary, but was "
+        fire_event(InvalidOptionYAML(option_name=cli_option_name))
-                "of type '{}'".format(type_name)
-            )
-    except ValidationException:
-        fire_event(InvalidVarsYAML())
         raise
 
 

core/dbt/constants.py

@@ -1,2 +1,10 @@
 SECRET_ENV_PREFIX = "DBT_ENV_SECRET_"
 DEFAULT_ENV_PLACEHOLDER = "DBT_DEFAULT_PLACEHOLDER"
+METADATA_ENV_PREFIX = "DBT_ENV_CUSTOM_ENV_"
+
+MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
+MAXIMUM_SEED_SIZE_NAME = "1MB"
+
+PIN_PACKAGE_URL = (
+    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"
+)

core/dbt/context/base.py

@@ -4,19 +4,22 @@ from typing import Any, Dict, NoReturn, Optional, Mapping, Iterable, Set, List
 
 from dbt import flags
 from dbt import tracking
+from dbt import utils
 from dbt.clients.jinja import get_rendered
 from dbt.clients.yaml_helper import yaml, safe_load, SafeLoader, Loader, Dumper  # noqa: F401
 from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
-from dbt.contracts.graph.compiled import CompiledResource
+from dbt.contracts.graph.nodes import Resource
 from dbt.exceptions import (
-    CompilationException,
+    SecretEnvVarLocationError,
+    EnvVarMissingError,
     MacroReturn,
-    raise_compiler_error,
+    RequiredVarNotFoundError,
-    raise_parsing_error,
+    SetStrictWrongTypeError,
-    disallow_secret_env_var,
+    ZipStrictWrongTypeError,
 )
 from dbt.events.functions import fire_event, get_invocation_id
-from dbt.events.types import MacroEventInfo, MacroEventDebug
+from dbt.events.types import JinjaLogInfo, JinjaLogDebug
+from dbt.events.contextvars import get_node_info
 from dbt.version import __version__ as dbt_version
 
 # These modules are added to the context. Consider alternative
@@ -126,18 +129,17 @@ class ContextMeta(type):
 
 
 class Var:
-    UndefinedVarError = "Required var '{}' not found in config:\nVars " "supplied to {} = {}"
     _VAR_NOTSET = object()
 
     def __init__(
         self,
         context: Mapping[str, Any],
         cli_vars: Mapping[str, Any],
-        node: Optional[CompiledResource] = None,
+        node: Optional[Resource] = None,
     ) -> None:
         self._context: Mapping[str, Any] = context
         self._cli_vars: Mapping[str, Any] = cli_vars
-        self._node: Optional[CompiledResource] = node
+        self._node: Optional[Resource] = node
         self._merged: Mapping[str, Any] = self._generate_merged()
 
     def _generate_merged(self) -> Mapping[str, Any]:
@@ -151,10 +153,7 @@ class Var:
             return "<Configuration>"
 
     def get_missing_var(self, var_name):
-        dct = {k: self._merged[k] for k in self._merged}
+        raise RequiredVarNotFoundError(var_name, self._merged, self._node)
-        pretty_vars = json.dumps(dct, sort_keys=True, indent=4)
-        msg = self.UndefinedVarError.format(var_name, self.node_name, pretty_vars)
-        raise_compiler_error(msg, self._node)
 
     def has_var(self, var_name: str):
         return var_name in self._merged
@@ -298,7 +297,7 @@ class BaseContext(metaclass=ContextMeta):
         """
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -313,8 +312,7 @@ class BaseContext(metaclass=ContextMeta):
 
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
+            raise EnvVarMissingError(var)
-            raise_parsing_error(msg)
 
     if os.environ.get("DBT_MACRO_DEBUGGING"):
 
@@ -495,7 +493,7 @@ class BaseContext(metaclass=ContextMeta):
         try:
             return set(value)
         except TypeError as e:
-            raise CompilationException(e)
+            raise SetStrictWrongTypeError(e)
 
     @contextmember("zip")
     @staticmethod
@@ -539,7 +537,7 @@ class BaseContext(metaclass=ContextMeta):
         try:
             return zip(*args)
         except TypeError as e:
-            raise CompilationException(e)
+            raise ZipStrictWrongTypeError(e)
 
     @contextmember
     @staticmethod
@@ -557,9 +555,9 @@ class BaseContext(metaclass=ContextMeta):
             {% endmacro %}"
         """
         if info:
-            fire_event(MacroEventInfo(msg=msg))
+            fire_event(JinjaLogInfo(msg=msg, node_info=get_node_info()))
         else:
-            fire_event(MacroEventDebug(msg=msg))
+            fire_event(JinjaLogDebug(msg=msg, node_info=get_node_info()))
         return ""
 
     @contextproperty
@@ -636,9 +634,8 @@ class BaseContext(metaclass=ContextMeta):
             {% endif %}
 
         This supports all flags defined in flags submodule (core/dbt/flags.py)
-        TODO: Replace with object that provides read-only access to flag values
         """
-        return flags
+        return flags.get_flag_obj()
 
     @contextmember
     @staticmethod
@@ -687,6 +684,19 @@ class BaseContext(metaclass=ContextMeta):
                 dict_diff.update({k: dict_a[k]})
         return dict_diff
 
+    @contextmember
+    @staticmethod
+    def local_md5(value: str) -> str:
+        """Calculates an MD5 hash of the given string.
+        It's called "local_md5" to emphasize that it runs locally in dbt (in jinja context) and not an MD5 SQL command.
+
+        :param value: The value to hash
+
+        Usage:
+            {% set value_hash = local_md5("hello world") %}
+        """
+        return utils.md5(value)
+
 
 def generate_base_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:
     ctx = BaseContext(cli_vars)

core/dbt/context/configured.py

@@ -8,7 +8,7 @@ from dbt.utils import MultiDict
 
 from dbt.context.base import contextproperty, contextmember, Var
 from dbt.context.target import TargetContext
-from dbt.exceptions import raise_parsing_error, disallow_secret_env_var
+from dbt.exceptions import EnvVarMissingError, SecretEnvVarLocationError
 
 
 class ConfiguredContext(TargetContext):
@@ -86,7 +86,7 @@ class SchemaYamlContext(ConfiguredContext):
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -104,8 +104,7 @@ class SchemaYamlContext(ConfiguredContext):
 
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
+            raise EnvVarMissingError(var)
-            raise_parsing_error(msg)
 
 
 class MacroResolvingContext(ConfiguredContext):

core/dbt/context/context_config.py

@@ -5,7 +5,7 @@ from typing import List, Iterator, Dict, Any, TypeVar, Generic
 
 from dbt.config import RuntimeConfig, Project, IsFQNResource
 from dbt.contracts.graph.model_config import BaseConfig, get_config_for, _listify
-from dbt.exceptions import InternalException
+from dbt.exceptions import DbtInternalError
 from dbt.node_types import NodeType
 from dbt.utils import fqn_search
 
@@ -45,6 +45,8 @@ class UnrenderedConfig(ConfigSource):
             model_configs = unrendered.get("tests")
         elif resource_type == NodeType.Metric:
             model_configs = unrendered.get("metrics")
+        elif resource_type == NodeType.Entity:
+            model_configs = unrendered.get("entities")
         elif resource_type == NodeType.Exposure:
             model_configs = unrendered.get("exposures")
         else:
@@ -70,6 +72,8 @@ class RenderedConfig(ConfigSource):
             model_configs = self.project.tests
         elif resource_type == NodeType.Metric:
             model_configs = self.project.metrics
+        elif resource_type == NodeType.Entity:
+            model_configs = self.project.entities
         elif resource_type == NodeType.Exposure:
             model_configs = self.project.exposures
         else:
@@ -89,7 +93,7 @@ class BaseContextConfigGenerator(Generic[T]):
             return self._active_project
         dependencies = self._active_project.load_dependencies()
         if project_name not in dependencies:
-            raise InternalException(
+            raise DbtInternalError(
                 f"Project name {project_name} not found in dependencies "
                 f"(found {list(dependencies)})"
             )
@@ -287,14 +291,14 @@ class ContextConfig:
 
             elif k in BaseConfig.mergebehavior["update"]:
                 if not isinstance(v, dict):
-                    raise InternalException(f"expected dict, got {v}")
+                    raise DbtInternalError(f"expected dict, got {v}")
                 if k in config_call_dict and isinstance(config_call_dict[k], dict):
                     config_call_dict[k].update(v)
                 else:
                     config_call_dict[k] = v
             elif k in BaseConfig.mergebehavior["dict_key_append"]:
                 if not isinstance(v, dict):
-                    raise InternalException(f"expected dict, got {v}")
+                    raise DbtInternalError(f"expected dict, got {v}")
                 if k in config_call_dict:  # should always be a dict
                     for key, value in v.items():
                         extend = False

core/dbt/context/docs.py

@@ -1,13 +1,12 @@
 from typing import Any, Dict, Union
 
 from dbt.exceptions import (
-    doc_invalid_args,
+    DocTargetNotFoundError,
-    doc_target_not_found,
+    DocArgsError,
 )
 from dbt.config.runtime import RuntimeConfig
-from dbt.contracts.graph.compiled import CompileResultNode
 from dbt.contracts.graph.manifest import Manifest
-from dbt.contracts.graph.parsed import ParsedMacro
+from dbt.contracts.graph.nodes import Macro, ResultNode
 
 from dbt.context.base import contextmember
 from dbt.context.configured import SchemaYamlContext
@@ -17,7 +16,7 @@ class DocsRuntimeContext(SchemaYamlContext):
     def __init__(
         self,
         config: RuntimeConfig,
-        node: Union[ParsedMacro, CompileResultNode],
+        node: Union[Macro, ResultNode],
         manifest: Manifest,
         current_project: str,
     ) -> None:
@@ -53,9 +52,9 @@ class DocsRuntimeContext(SchemaYamlContext):
         elif len(args) == 2:
             doc_package_name, doc_name = args
         else:
-            doc_invalid_args(self.node, args)
+            raise DocArgsError(self.node, args)
 
-        # ParsedDocumentation
+        # Documentation
         target_doc = self.manifest.resolve_doc(
             doc_name,
             doc_package_name,
@@ -69,7 +68,9 @@ class DocsRuntimeContext(SchemaYamlContext):
                 # TODO CT-211
                 source_file.add_node(self.node.unique_id)  # type: ignore[union-attr]
         else:
-            doc_target_not_found(self.node, doc_name, doc_package_name)
+            raise DocTargetNotFoundError(
+                node=self.node, target_doc_name=doc_name, target_doc_package=doc_package_name
+            )
 
         return target_doc.block_contents
 

core/dbt/context/exceptions_jinja.py

@@ -0,0 +1,144 @@
+import functools
+from typing import NoReturn
+
+from dbt.events.functions import warn_or_error
+from dbt.events.helpers import env_secrets, scrub_secrets
+from dbt.events.types import JinjaLogWarning
+
+from dbt.exceptions import (
+    DbtRuntimeError,
+    MissingConfigError,
+    MissingMaterializationError,
+    MissingRelationError,
+    AmbiguousAliasError,
+    AmbiguousCatalogMatchError,
+    CacheInconsistencyError,
+    DataclassNotDictError,
+    CompilationError,
+    DbtDatabaseError,
+    DependencyNotFoundError,
+    DependencyError,
+    DuplicatePatchPathError,
+    DuplicateResourceNameError,
+    PropertyYMLError,
+    NotImplementedError,
+    RelationWrongTypeError,
+)
+
+
+def warn(msg, node=None):
+    warn_or_error(JinjaLogWarning(msg=msg), node=node)
+    return ""
+
+
+def missing_config(model, name) -> NoReturn:
+    raise MissingConfigError(unique_id=model.unique_id, name=name)
+
+
+def missing_materialization(model, adapter_type) -> NoReturn:
+    raise MissingMaterializationError(
+        materialization=model.config.materialized, adapter_type=adapter_type
+    )
+
+
+def missing_relation(relation, model=None) -> NoReturn:
+    raise MissingRelationError(relation, model)
+
+
+def raise_ambiguous_alias(node_1, node_2, duped_name=None) -> NoReturn:
+    raise AmbiguousAliasError(node_1, node_2, duped_name)
+
+
+def raise_ambiguous_catalog_match(unique_id, match_1, match_2) -> NoReturn:
+    raise AmbiguousCatalogMatchError(unique_id, match_1, match_2)
+
+
+def raise_cache_inconsistent(message) -> NoReturn:
+    raise CacheInconsistencyError(message)
+
+
+def raise_dataclass_not_dict(obj) -> NoReturn:
+    raise DataclassNotDictError(obj)
+
+
+def raise_compiler_error(msg, node=None) -> NoReturn:
+    raise CompilationError(msg, node)
+
+
+def raise_database_error(msg, node=None) -> NoReturn:
+    raise DbtDatabaseError(msg, node)
+
+
+def raise_dep_not_found(node, node_description, required_pkg) -> NoReturn:
+    raise DependencyNotFoundError(node, node_description, required_pkg)
+
+
+def raise_dependency_error(msg) -> NoReturn:
+    raise DependencyError(scrub_secrets(msg, env_secrets()))
+
+
+def raise_duplicate_patch_name(patch_1, existing_patch_path) -> NoReturn:
+    raise DuplicatePatchPathError(patch_1, existing_patch_path)
+
+
+def raise_duplicate_resource_name(node_1, node_2) -> NoReturn:
+    raise DuplicateResourceNameError(node_1, node_2)
+
+
+def raise_invalid_property_yml_version(path, issue) -> NoReturn:
+    raise PropertyYMLError(path, issue)
+
+
+def raise_not_implemented(msg) -> NoReturn:
+    raise NotImplementedError(msg)
+
+
+def relation_wrong_type(relation, expected_type, model=None) -> NoReturn:
+    raise RelationWrongTypeError(relation, expected_type, model)
+
+
+# Update this when a new function should be added to the
+# dbt context's `exceptions` key!
+CONTEXT_EXPORTS = {
+    fn.__name__: fn
+    for fn in [
+        warn,
+        missing_config,
+        missing_materialization,
+        missing_relation,
+        raise_ambiguous_alias,
+        raise_ambiguous_catalog_match,
+        raise_cache_inconsistent,
+        raise_dataclass_not_dict,
+        raise_compiler_error,
+        raise_database_error,
+        raise_dep_not_found,
+        raise_dependency_error,
+        raise_duplicate_patch_name,
+        raise_duplicate_resource_name,
+        raise_invalid_property_yml_version,
+        raise_not_implemented,
+        relation_wrong_type,
+    ]
+}
+
+
+# wraps context based exceptions in node info
+def wrapper(model):
+    def wrap(func):
+        @functools.wraps(func)
+        def inner(*args, **kwargs):
+            try:
+                return func(*args, **kwargs)
+            except DbtRuntimeError as exc:
+                exc.add_node(model)
+                raise exc
+
+        return inner
+
+    return wrap
+
+
+def wrapped_exports(model):
+    wrap = wrapper(model)
+    return {name: wrap(export) for name, export in CONTEXT_EXPORTS.items()}

core/dbt/context/macro_resolver.py

@@ -1,10 +1,10 @@
 from typing import Dict, MutableMapping, Optional
-from dbt.contracts.graph.parsed import ParsedMacro
+from dbt.contracts.graph.nodes import Macro
-from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
+from dbt.exceptions import DuplicateMacroNameError, PackageNotFoundForMacroError
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
 from dbt.clients.jinja import MacroGenerator
 
-MacroNamespace = Dict[str, ParsedMacro]
+MacroNamespace = Dict[str, Macro]
 
 
 # This class builds the MacroResolver by adding macros
@@ -21,7 +21,7 @@ MacroNamespace = Dict[str, ParsedMacro]
 class MacroResolver:
     def __init__(
         self,
-        macros: MutableMapping[str, ParsedMacro],
+        macros: MutableMapping[str, Macro],
         root_project_name: str,
         internal_package_names,
     ) -> None:
@@ -77,7 +77,7 @@ class MacroResolver:
     def _add_macro_to(
         self,
         package_namespaces: Dict[str, MacroNamespace],
-        macro: ParsedMacro,
+        macro: Macro,
     ):
         if macro.package_name in package_namespaces:
             namespace = package_namespaces[macro.package_name]
@@ -86,10 +86,10 @@ class MacroResolver:
             package_namespaces[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro, macro, macro.package_name)
+            raise DuplicateMacroNameError(macro, macro, macro.package_name)
         package_namespaces[macro.package_name][macro.name] = macro
 
-    def add_macro(self, macro: ParsedMacro):
+    def add_macro(self, macro: Macro):
         macro_name: str = macro.name
 
         # internal macros (from plugins) will be processed separately from
@@ -187,7 +187,7 @@ class TestMacroNamespace:
         elif package_name in self.macro_resolver.packages:
             macro = self.macro_resolver.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
+            raise PackageNotFoundForMacroError(package_name)
         if not macro:
             return None
         macro_func = MacroGenerator(macro, self.ctx, self.node, self.thread_ctx)

core/dbt/context/macros.py

@@ -1,9 +1,9 @@
 from typing import Any, Dict, Iterable, Union, Optional, List, Iterator, Mapping, Set
 
 from dbt.clients.jinja import MacroGenerator, MacroStack
-from dbt.contracts.graph.parsed import ParsedMacro
+from dbt.contracts.graph.nodes import Macro
 from dbt.include.global_project import PROJECT_NAME as GLOBAL_PROJECT_NAME
-from dbt.exceptions import raise_duplicate_macro_name, raise_compiler_error
+from dbt.exceptions import DuplicateMacroNameError, PackageNotFoundForMacroError
 
 
 FlatNamespace = Dict[str, MacroGenerator]
@@ -75,7 +75,7 @@ class MacroNamespace(Mapping):
         elif package_name in self.packages:
             return self.packages[package_name].get(name)
         else:
-            raise_compiler_error(f"Could not find package '{package_name}'")
+            raise PackageNotFoundForMacroError(package_name)
 
 
 # This class builds the MacroNamespace by adding macros to
@@ -112,7 +112,7 @@ class MacroNamespaceBuilder:
     def _add_macro_to(
         self,
         hierarchy: Dict[str, FlatNamespace],
-        macro: ParsedMacro,
+        macro: Macro,
         macro_func: MacroGenerator,
     ):
         if macro.package_name in hierarchy:
@@ -122,10 +122,10 @@ class MacroNamespaceBuilder:
             hierarchy[macro.package_name] = namespace
 
         if macro.name in namespace:
-            raise_duplicate_macro_name(macro_func.macro, macro, macro.package_name)
+            raise DuplicateMacroNameError(macro_func.macro, macro, macro.package_name)
         hierarchy[macro.package_name][macro.name] = macro_func
 
-    def add_macro(self, macro: ParsedMacro, ctx: Dict[str, Any]):
+    def add_macro(self, macro: Macro, ctx: Dict[str, Any]):
         macro_name: str = macro.name
 
         # MacroGenerator is in clients/jinja.py
@@ -147,13 +147,11 @@ class MacroNamespaceBuilder:
             elif macro.package_name == self.root_package:
                 self.globals[macro_name] = macro_func
 
-    def add_macros(self, macros: Iterable[ParsedMacro], ctx: Dict[str, Any]):
+    def add_macros(self, macros: Iterable[Macro], ctx: Dict[str, Any]):
         for macro in macros:
             self.add_macro(macro, ctx)
 
-    def build_namespace(
+    def build_namespace(self, macros: Iterable[Macro], ctx: Dict[str, Any]) -> MacroNamespace:
-        self, macros: Iterable[ParsedMacro], ctx: Dict[str, Any]
-    ) -> MacroNamespace:
         self.add_macros(macros, ctx)
 
         # Iterate in reverse-order and overwrite: the packages that are first

core/dbt/context/providers.py

@@ -19,46 +19,51 @@ from dbt.adapters.factory import get_adapter, get_adapter_package_names, get_ada
 from dbt.clients import agate_helper
 from dbt.clients.jinja import get_rendered, MacroGenerator, MacroStack
 from dbt.config import RuntimeConfig, Project
-from .base import contextmember, contextproperty, Var
-from .configured import FQNLookup
-from .context_config import ContextConfig
 from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
+from dbt.context.base import contextmember, contextproperty, Var
+from dbt.context.configured import FQNLookup
+from dbt.context.context_config import ContextConfig
+from dbt.context.exceptions_jinja import wrapped_exports
 from dbt.context.macro_resolver import MacroResolver, TestMacroNamespace
-from .macros import MacroNamespaceBuilder, MacroNamespace
+from dbt.context.macros import MacroNamespaceBuilder, MacroNamespace
-from .manifest import ManifestContext
+from dbt.context.manifest import ManifestContext
 from dbt.contracts.connection import AdapterResponse
 from dbt.contracts.graph.manifest import Manifest, Disabled
-from dbt.contracts.graph.compiled import (
+from dbt.contracts.graph.nodes import (
-    CompiledResource,
+    Macro,
-    CompiledSeedNode,
+    Exposure,
+    Metric,
+    Entity,
+    SeedNode,
+    SourceDefinition,
+    Resource,
     ManifestNode,
 )
-from dbt.contracts.graph.parsed import (
-    ParsedMacro,
-    ParsedExposure,
-    ParsedMetric,
-    ParsedSeedNode,
-    ParsedSourceDefinition,
-)
 from dbt.contracts.graph.metrics import MetricReference, ResolvedMetricReference
-from dbt.contracts.util import get_metadata_env
+from dbt.events.functions import get_metadata_vars
 from dbt.exceptions import (
-    CompilationException,
+    CompilationError,
-    ParsingException,
+    ConflictingConfigKeysError,
-    InternalException,
+    SecretEnvVarLocationError,
-    ValidationException,
+    EnvVarMissingError,
-    RuntimeException,
+    DbtInternalError,
-    macro_invalid_dispatch_arg,
+    InlineModelConfigError,
-    missing_config,
+    NumberSourceArgsError,
-    raise_compiler_error,
+    PersistDocsValueTypeError,
-    ref_invalid_args,
+    LoadAgateTableNotSeedError,
-    metric_invalid_args,
+    LoadAgateTableValueError,
-    ref_target_not_found,
+    MacroDispatchArgError,
-    target_not_found,
+    MacrosSourcesUnWriteableError,
-    ref_bad_context,
+    MetricArgsError,
-    wrapped_exports,
+    MissingConfigError,
-    raise_parsing_error,
+    OperationsCannotRefEphemeralNodesError,
-    disallow_secret_env_var,
+    PackageNotInDepsError,
+    ParsingError,
+    RefBadContextError,
+    RefArgsError,
+    DbtRuntimeError,
+    TargetNotFoundError,
+    DbtValidationError,
 )
 from dbt.config import IsFQNResource
 from dbt.node_types import NodeType, ModelLanguage
@@ -140,10 +145,10 @@ class BaseDatabaseWrapper:
                 f'`adapter.dispatch("{suggest_macro_name}", '
                 f'macro_namespace="{suggest_macro_namespace}")`?'
             )
-            raise CompilationException(msg)
+            raise CompilationError(msg)
 
         if packages is not None:
-            raise macro_invalid_dispatch_arg(macro_name)
+            raise MacroDispatchArgError(macro_name)
 
         namespace = macro_namespace
 
@@ -155,7 +160,7 @@ class BaseDatabaseWrapper:
                 search_packages = [self.config.project_name, namespace]
         else:
             # Not a string and not None so must be a list
-            raise CompilationException(
+            raise CompilationError(
                 f"In adapter.dispatch, got a list macro_namespace argument "
                 f'("{macro_namespace}"), but macro_namespace should be None or a string.'
             )
@@ -168,8 +173,8 @@ class BaseDatabaseWrapper:
                 try:
                     # this uses the namespace from the context
                     macro = self._namespace.get_from_package(package_name, search_name)
-                except CompilationException:
+                except CompilationError:
-                    # Only raise CompilationException if macro is not found in
+                    # Only raise CompilationError if macro is not found in
                     # any package
                     macro = None
 
@@ -182,8 +187,8 @@ class BaseDatabaseWrapper:
                     return macro
 
         searched = ", ".join(repr(a) for a in attempts)
-        msg = f"In dispatch: No macro named '{macro_name}' found\n" f"    Searched for: {searched}"
+        msg = f"In dispatch: No macro named '{macro_name}' found\n    Searched for: {searched}"
-        raise CompilationException(msg)
+        raise CompilationError(msg)
 
 
 class BaseResolver(metaclass=abc.ABCMeta):
@@ -219,13 +224,13 @@ class BaseRefResolver(BaseResolver):
 
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
-            raise CompilationException(
+            raise CompilationError(
-                f"The name argument to ref() must be a string, got " f"{type(name)}"
+                f"The name argument to ref() must be a string, got {type(name)}"
             )
 
         if package is not None and not isinstance(package, str):
-            raise CompilationException(
+            raise CompilationError(
-                f"The package argument to ref() must be a string or None, got " f"{type(package)}"
+                f"The package argument to ref() must be a string or None, got {type(package)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
@@ -237,7 +242,7 @@ class BaseRefResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         return self.resolve(name, package)
 
@@ -249,21 +254,19 @@ class BaseSourceResolver(BaseResolver):
 
     def validate_args(self, source_name: str, table_name: str):
         if not isinstance(source_name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The source name (first) argument to source() must be a "
                 f"string, got {type(source_name)}"
             )
         if not isinstance(table_name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The table name (second) argument to source() must be a "
                 f"string, got {type(table_name)}"
             )
 
     def __call__(self, *args: str) -> RelationProxy:
         if len(args) != 2:
-            raise_compiler_error(
+            raise NumberSourceArgsError(args, node=self.model)
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
-            )
         self.validate_args(args[0], args[1])
         return self.resolve(args[0], args[1])
 
@@ -280,12 +283,12 @@ class BaseMetricResolver(BaseResolver):
 
     def validate_args(self, name: str, package: Optional[str]):
         if not isinstance(name, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The name argument to metric() must be a string, got {type(name)}"
             )
 
         if package is not None and not isinstance(package, str):
-            raise CompilationException(
+            raise CompilationError(
                 f"The package argument to metric() must be a string or None, got {type(package)}"
             )
 
@@ -298,7 +301,7 @@ class BaseMetricResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            metric_invalid_args(self.model, args)
+            raise MetricArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         return self.resolve(name, package)
 
@@ -319,12 +322,7 @@ class ParseConfigObject(Config):
             if oldkey in config:
                 newkey = oldkey.replace("_", "-")
                 if newkey in config:
-                    raise_compiler_error(
+                    raise ConflictingConfigKeysError(oldkey, newkey, node=self.model)
-                        'Invalid config, has conflicting keys "{}" and "{}"'.format(
-                            oldkey, newkey
-                        ),
-                        self.model,
-                    )
                 config[newkey] = config.pop(oldkey)
         return config
 
@@ -334,14 +332,14 @@ class ParseConfigObject(Config):
         elif len(args) == 0 and len(kwargs) > 0:
             opts = kwargs
         else:
-            raise_compiler_error("Invalid inline model config", self.model)
+            raise InlineModelConfigError(node=self.model)
 
         opts = self._transform_config(opts)
 
         # it's ok to have a parse context with no context config, but you must
         # not call it!
         if self.context_config is None:
-            raise RuntimeException("At parse time, did not receive a context config")
+            raise DbtRuntimeError("At parse time, did not receive a context config")
         self.context_config.add_config_call(opts)
         return ""
 
@@ -382,7 +380,7 @@ class RuntimeConfigObject(Config):
         else:
             result = self.model.config.get(name, default)
         if result is _MISSING:
-            missing_config(self.model, name)
+            raise MissingConfigError(unique_id=self.model.unique_id, name=name)
         return result
 
     def require(self, name, validator=None):
@@ -404,20 +402,14 @@ class RuntimeConfigObject(Config):
     def persist_relation_docs(self) -> bool:
         persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
-            raise_compiler_error(
+            raise PersistDocsValueTypeError(persist_docs)
-                f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
 
         return persist_docs.get("relation", False)
 
     def persist_column_docs(self) -> bool:
         persist_docs = self.get("persist_docs", default={})
         if not isinstance(persist_docs, dict):
-            raise_compiler_error(
+            raise PersistDocsValueTypeError(persist_docs)
-                f"Invalid value provided for 'persist_docs'. Expected dict "
-                f"but received {type(persist_docs)}"
-            )
 
         return persist_docs.get("columns", False)
 
@@ -476,10 +468,11 @@ class RuntimeRefResolver(BaseRefResolver):
         )
 
         if target_model is None or isinstance(target_model, Disabled):
-            ref_target_not_found(
+            raise TargetNotFoundError(
-                self.model,
+                node=self.model,
-                target_name,
+                target_name=target_name,
-                target_package,
+                target_kind="node",
+                target_package=target_package,
                 disabled=isinstance(target_model, Disabled),
             )
         self.validate(target_model, target_name, target_package)
@@ -497,7 +490,7 @@ class RuntimeRefResolver(BaseRefResolver):
     ) -> None:
         if resolved.unique_id not in self.model.depends_on.nodes:
             args = self._repack_args(target_name, target_package)
-            ref_bad_context(self.model, args)
+            raise RefBadContextError(node=self.model, args=args)
 
 
 class OperationRefResolver(RuntimeRefResolver):
@@ -512,13 +505,8 @@ class OperationRefResolver(RuntimeRefResolver):
     def create_relation(self, target_model: ManifestNode, name: str) -> RelationProxy:
         if target_model.is_ephemeral_model:
             # In operations, we can't ref() ephemeral nodes, because
-            # ParsedMacros do not support set_cte
+            # Macros do not support set_cte
-            raise_compiler_error(
+            raise OperationsCannotRefEphemeralNodesError(target_model.name, node=self.model)
-                "Operations can not ref() ephemeral nodes, but {} is ephemeral".format(
-                    target_model.name
-                ),
-                self.model,
-            )
         else:
             return super().create_relation(target_model, name)
 
@@ -541,7 +529,7 @@ class RuntimeSourceResolver(BaseSourceResolver):
         )
 
         if target_source is None or isinstance(target_source, Disabled):
-            target_not_found(
+            raise TargetNotFoundError(
                 node=self.model,
                 target_name=f"{source_name}.{table_name}",
                 target_kind="source",
@@ -568,7 +556,7 @@ class RuntimeMetricResolver(BaseMetricResolver):
         )
 
         if target_metric is None or isinstance(target_metric, Disabled):
-            target_not_found(
+            raise TargetNotFoundError(
                 node=self.model,
                 target_name=target_name,
                 target_kind="metric",
@@ -584,9 +572,9 @@ class ModelConfiguredVar(Var):
         self,
         context: Dict[str, Any],
         config: RuntimeConfig,
-        node: CompiledResource,
+        node: Resource,
     ) -> None:
-        self._node: CompiledResource
+        self._node: Resource
         self._config: RuntimeConfig = config
         super().__init__(context, config.cli_vars, node=node)
 
@@ -597,7 +585,7 @@ class ModelConfiguredVar(Var):
         if package_name != self._config.project_name:
             if package_name not in dependencies:
                 # I don't think this is actually reachable
-                raise_compiler_error(f"Node package named {package_name} not found!", self._node)
+                raise PackageNotInDepsError(package_name, node=self._node)
             yield dependencies[package_name]
         yield self._config
 
@@ -687,10 +675,10 @@ class ProviderContext(ManifestContext):
         context_config: Optional[ContextConfig],
     ) -> None:
         if provider is None:
-            raise InternalException(f"Invalid provider given to context: {provider}")
+            raise DbtInternalError(f"Invalid provider given to context: {provider}")
         # mypy appeasement - we know it'll be a RuntimeConfig
         self.config: RuntimeConfig
-        self.model: Union[ParsedMacro, ManifestNode] = model
+        self.model: Union[Macro, ManifestNode] = model
         super().__init__(config, manifest, model.package_name)
         self.sql_results: Dict[str, AttrDict] = {}
         self.context_config: Optional[ContextConfig] = context_config
@@ -713,7 +701,7 @@ class ProviderContext(ManifestContext):
 
     @contextproperty
     def dbt_metadata_envs(self) -> Dict[str, str]:
-        return get_metadata_env()
+        return get_metadata_vars()
 
     @contextproperty
     def invocation_args_dict(self):
@@ -764,7 +752,7 @@ class ProviderContext(ManifestContext):
                         return
                     elif value == arg:
                         return
-                raise ValidationException(
+                raise DbtValidationError(
                     'Expected value "{}" to be one of {}'.format(value, ",".join(map(str, args)))
                 )
 
@@ -779,8 +767,8 @@ class ProviderContext(ManifestContext):
     @contextmember
     def write(self, payload: str) -> str:
         # macros/source defs aren't 'writeable'.
-        if isinstance(self.model, (ParsedMacro, ParsedSourceDefinition)):
+        if isinstance(self.model, (Macro, SourceDefinition)):
-            raise_compiler_error('cannot "write" macros or sources')
+            raise MacrosSourcesUnWriteableError(node=self.model)
         self.model.build_path = self.model.write_node(self.config.target_path, "run", payload)
         return ""
 
@@ -795,20 +783,19 @@ class ProviderContext(ManifestContext):
         try:
             return func(*args, **kwargs)
         except Exception:
-            raise_compiler_error(message_if_exception, self.model)
+            raise CompilationError(message_if_exception, self.model)
 
     @contextmember
     def load_agate_table(self) -> agate.Table:
-        if not isinstance(self.model, (ParsedSeedNode, CompiledSeedNode)):
+        if not isinstance(self.model, SeedNode):
-            raise_compiler_error(
+            raise LoadAgateTableNotSeedError(self.model.resource_type, node=self.model)
-                "can only load_agate_table for seeds (got a {})".format(self.model.resource_type)
+        assert self.model.root_path
-            )
         path = os.path.join(self.model.root_path, self.model.original_file_path)
         column_types = self.model.config.column_types
         try:
             table = agate_helper.from_csv(path, text_columns=column_types)
         except ValueError as e:
-            raise_compiler_error(str(e))
+            raise LoadAgateTableValueError(e, node=self.model)
         table.original_abspath = os.path.abspath(path)
         return table
 
@@ -1199,7 +1186,7 @@ class ProviderContext(ManifestContext):
             "https://docs.getdbt.com/reference/dbt-jinja-functions/dispatch)"
             " adapter_macro was called for: {macro_name}".format(macro_name=name)
         )
-        raise CompilationException(msg)
+        raise CompilationError(msg)
 
     @contextmember
     def env_var(self, var: str, default: Optional[str] = None) -> str:
@@ -1210,7 +1197,7 @@ class ProviderContext(ManifestContext):
         """
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -1219,7 +1206,13 @@ class ProviderContext(ManifestContext):
         if return_value is not None:
             # Save the env_var value in the manifest and the var name in the source_file.
             # If this is compiling, do not save because it's irrelevant to parsing.
-            if self.model and not hasattr(self.model, "compiled"):
+            compiling = (
+                True
+                if hasattr(self.model, "compiled")
+                and getattr(self.model, "compiled", False) is True
+                else False
+            )
+            if self.model and not compiling:
                 # If the environment variable is set from a default, store a string indicating
                 # that so we can skip partial parsing.  Otherwise the file will be scheduled for
                 # reparsing. If the default changes, the file will have been updated and therefore
@@ -1237,8 +1230,7 @@ class ProviderContext(ManifestContext):
                         source_file.env_vars.append(var)  # type: ignore[union-attr]
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
+            raise EnvVarMissingError(var)
-            raise_parsing_error(msg)
 
     @contextproperty
     def selected_resources(self) -> List[str]:
@@ -1257,7 +1249,7 @@ class ProviderContext(ManifestContext):
             and self.context_macro_stack.call_stack[1] == "macro.dbt.statement"
             and "materialization" in self.context_macro_stack.call_stack[0]
         ):
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f"submit_python_job is not intended to be called here, at model {parsed_model['alias']}, with macro call_stack {self.context_macro_stack.call_stack}."
             )
         return self.adapter.submit_python_job(parsed_model, compiled_code)
@@ -1274,7 +1266,7 @@ class MacroContext(ProviderContext):
 
     def __init__(
         self,
-        model: ParsedMacro,
+        model: Macro,
         config: RuntimeConfig,
         manifest: Manifest,
         provider: Provider,
@@ -1389,7 +1381,7 @@ def generate_parser_model_context(
 
 
 def generate_generate_name_macro_context(
-    macro: ParsedMacro,
+    macro: Macro,
     config: RuntimeConfig,
     manifest: Manifest,
 ) -> Dict[str, Any]:
@@ -1407,7 +1399,7 @@ def generate_runtime_model_context(
 
 
 def generate_runtime_macro_context(
-    macro: ParsedMacro,
+    macro: Macro,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: Optional[str],
@@ -1419,7 +1411,7 @@ def generate_runtime_macro_context(
 class ExposureRefResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) not in (1, 2):
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.model.refs.append(list(args))
         return ""
 
@@ -1427,15 +1419,21 @@ class ExposureRefResolver(BaseResolver):
 class ExposureSourceResolver(BaseResolver):
     def __call__(self, *args) -> str:
         if len(args) != 2:
-            raise_compiler_error(
+            raise NumberSourceArgsError(args, node=self.model)
-                f"source() takes exactly two arguments ({len(args)} given)", self.model
-            )
         self.model.sources.append(list(args))
         return ""
 
 
+class ExposureMetricResolver(BaseResolver):
+    def __call__(self, *args) -> str:
+        if len(args) not in (1, 2):
+            raise MetricArgsError(node=self.model, args=args)
+        self.model.metrics.append(list(args))
+        return ""
+
+
 def generate_parse_exposure(
-    exposure: ParsedExposure,
+    exposure: Exposure,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: str,
@@ -1454,6 +1452,12 @@ def generate_parse_exposure(
             project,
             manifest,
         ),
+        "metric": ExposureMetricResolver(
+            None,
+            exposure,
+            project,
+            manifest,
+        ),
     }
 
 
@@ -1465,21 +1469,21 @@ class MetricRefResolver(BaseResolver):
         elif len(args) == 2:
             package, name = args
         else:
-            ref_invalid_args(self.model, args)
+            raise RefArgsError(node=self.model, args=args)
         self.validate_args(name, package)
         self.model.refs.append(list(args))
         return ""
 
     def validate_args(self, name, package):
         if not isinstance(name, str):
-            raise ParsingException(
+            raise ParsingError(
                 f"In a metrics section in {self.model.original_file_path} "
                 "the name argument to ref() must be a string"
             )
 
 
 def generate_parse_metrics(
-    metric: ParsedMetric,
+    metric: Metric,
     config: RuntimeConfig,
     manifest: Manifest,
     package_name: str,
@@ -1501,6 +1505,44 @@ def generate_parse_metrics(
     }
 
 
+class EntityRefResolver(BaseResolver):
+    def __call__(self, *args) -> str:
+        package = None
+        if len(args) == 1:
+            name = args[0]
+        elif len(args) == 2:
+            package, name = args
+        else:
+            raise RefArgsError(node=self.model, args=args)
+        self.validate_args(name, package)
+        self.model.refs.append(list(args))
+        return ""
+
+    def validate_args(self, name, package):
+        if not isinstance(name, str):
+            raise ParsingError(
+                f"In the entity associated with {self.model.original_file_path} "
+                "the name argument to ref() must be a string"
+            )
+
+
+def generate_parse_entities(
+    entity: Entity,
+    config: RuntimeConfig,
+    manifest: Manifest,
+    package_name: str,
+) -> Dict[str, Any]:
+    project = config.load_dependencies()[package_name]
+    return {
+        "ref": EntityRefResolver(
+            None,
+            entity,
+            project,
+            manifest,
+        ),
+    }
+
+
 # This class is currently used by the schema parser in order
 # to limit the number of macros in the context by using
 # the TestMacroNamespace
@@ -1555,7 +1597,7 @@ class TestContext(ProviderContext):
     def env_var(self, var: str, default: Optional[str] = None) -> str:
         return_value = None
         if var.startswith(SECRET_ENV_PREFIX):
-            disallow_secret_env_var(var)
+            raise SecretEnvVarLocationError(var)
         if var in os.environ:
             return_value = os.environ[var]
         elif default is not None:
@@ -1581,8 +1623,7 @@ class TestContext(ProviderContext):
                     source_file.add_env_var(var, yaml_key, name)  # type: ignore[union-attr]
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
+            raise EnvVarMissingError(var)
-            raise_parsing_error(msg)
 
 
 def generate_test_context(

core/dbt/context/secret.py

@@ -4,7 +4,7 @@ from typing import Any, Dict, Optional
 from .base import BaseContext, contextmember
 
 from dbt.constants import SECRET_ENV_PREFIX, DEFAULT_ENV_PLACEHOLDER
-from dbt.exceptions import raise_parsing_error
+from dbt.exceptions import EnvVarMissingError
 
 
 SECRET_PLACEHOLDER = "$$$DBT_SECRET_START$$${}$$$DBT_SECRET_END$$$"
@@ -50,8 +50,7 @@ class SecretContext(BaseContext):
                 self.env_vars[var] = return_value if var in os.environ else DEFAULT_ENV_PLACEHOLDER
             return return_value
         else:
-            msg = f"Env var required but not provided: '{var}'"
+            raise EnvVarMissingError(var)
-            raise_parsing_error(msg)
 
 
 def generate_secret_context(cli_vars: Dict[str, Any]) -> Dict[str, Any]:

core/dbt/contracts/connection.py

@@ -12,10 +12,11 @@ from typing import (
     List,
     Callable,
 )
-from dbt.exceptions import InternalException
+from dbt.exceptions import DbtInternalError
 from dbt.utils import translate_aliases
 from dbt.events.functions import fire_event
 from dbt.events.types import NewConnectionOpening
+from dbt.events.contextvars import get_node_info
 from typing_extensions import Protocol
 from dbt.dataclass_schema import (
     dbtClassMixin,
@@ -93,8 +94,8 @@ class Connection(ExtensibleDbtClassMixin, Replaceable):
                 # this will actually change 'self._handle'.
                 self._handle.resolve(self)
             except RecursionError as exc:
-                raise InternalException(
+                raise DbtInternalError(
-                    "A connection's open() method attempted to read the " "handle value"
+                    "A connection's open() method attempted to read the handle value"
                 ) from exc
         return self._handle
 
@@ -112,7 +113,9 @@ class LazyHandle:
         self.opener = opener
 
     def resolve(self, connection: Connection) -> Connection:
-        fire_event(NewConnectionOpening(connection_state=connection.state))
+        fire_event(
+            NewConnectionOpening(connection_state=connection.state, node_info=get_node_info())
+        )
         return self.opener(connection)
 
 

core/dbt/contracts/files.py

@@ -1,18 +1,16 @@
 import hashlib
 import os
 from dataclasses import dataclass, field
+
 from mashumaro.types import SerializableType
 from typing import List, Optional, Union, Dict, Any
 
+from dbt.constants import MAXIMUM_SEED_SIZE
 from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
 from .util import SourceKey
 
 
-MAXIMUM_SEED_SIZE = 1 * 1024 * 1024
-MAXIMUM_SEED_SIZE_NAME = "1MB"
-
-
 class ParseFileType(StrEnum):
     Macro = "macro"
     Model = "model"
@@ -229,6 +227,7 @@ class SchemaSourceFile(BaseSourceFile):
     sources: List[str] = field(default_factory=list)
     exposures: List[str] = field(default_factory=list)
     metrics: List[str] = field(default_factory=list)
+    entities: List[str] = field(default_factory=list)
     # node patches contain models, seeds, snapshots, analyses
     ndp: List[str] = field(default_factory=list)
     # any macro patches in this file by macro unique_id.

core/dbt/contracts/graph/compiled.py

@@ -1,235 +0,0 @@
-from dbt.contracts.graph.parsed import (
-    HasTestMetadata,
-    ParsedNode,
-    ParsedAnalysisNode,
-    ParsedSingularTestNode,
-    ParsedHookNode,
-    ParsedModelNode,
-    ParsedExposure,
-    ParsedMetric,
-    ParsedResource,
-    ParsedRPCNode,
-    ParsedSqlNode,
-    ParsedGenericTestNode,
-    ParsedSeedNode,
-    ParsedSnapshotNode,
-    ParsedSourceDefinition,
-    SeedConfig,
-    TestConfig,
-    same_seeds,
-)
-from dbt.node_types import NodeType
-from dbt.contracts.util import Replaceable
-
-from dbt.dataclass_schema import dbtClassMixin
-from dataclasses import dataclass, field
-from typing import Optional, List, Union, Dict, Type
-
-
-@dataclass
-class InjectedCTE(dbtClassMixin, Replaceable):
-    id: str
-    sql: str
-
-
-@dataclass
-class CompiledNodeMixin(dbtClassMixin):
-    # this is a special mixin class to provide a required argument. If a node
-    # is missing a `compiled` flag entirely, it must not be a CompiledNode.
-    compiled: bool
-
-
-@dataclass
-class CompiledNode(ParsedNode, CompiledNodeMixin):
-    compiled_code: Optional[str] = None
-    extra_ctes_injected: bool = False
-    extra_ctes: List[InjectedCTE] = field(default_factory=list)
-    relation_name: Optional[str] = None
-    _pre_injected_sql: Optional[str] = None
-
-    def set_cte(self, cte_id: str, sql: str):
-        """This is the equivalent of what self.extra_ctes[cte_id] = sql would
-        do if extra_ctes were an OrderedDict
-        """
-        for cte in self.extra_ctes:
-            if cte.id == cte_id:
-                cte.sql = sql
-                break
-        else:
-            self.extra_ctes.append(InjectedCTE(id=cte_id, sql=sql))
-
-    def __post_serialize__(self, dct):
-        dct = super().__post_serialize__(dct)
-        if "_pre_injected_sql" in dct:
-            del dct["_pre_injected_sql"]
-        return dct
-
-
-@dataclass
-class CompiledAnalysisNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Analysis]})
-
-
-@dataclass
-class CompiledHookNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Operation]})
-    index: Optional[int] = None
-
-
-@dataclass
-class CompiledModelNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Model]})
-
-
-# TODO: rm?
-@dataclass
-class CompiledRPCNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.RPCCall]})
-
-
-@dataclass
-class CompiledSqlNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.SqlOperation]})
-
-
-@dataclass
-class CompiledSeedNode(CompiledNode):
-    # keep this in sync with ParsedSeedNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Seed]})
-    config: SeedConfig = field(default_factory=SeedConfig)
-
-    @property
-    def empty(self):
-        """Seeds are never empty"""
-        return False
-
-    def same_body(self, other) -> bool:
-        return same_seeds(self, other)
-
-
-@dataclass
-class CompiledSnapshotNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Snapshot]})
-
-
-@dataclass
-class CompiledSingularTestNode(CompiledNode):
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    # Was not able to make mypy happy and keep the code working. We need to
-    # refactor the various configs.
-    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
-
-
-@dataclass
-class CompiledGenericTestNode(CompiledNode, HasTestMetadata):
-    # keep this in sync with ParsedGenericTestNode!
-    resource_type: NodeType = field(metadata={"restrict": [NodeType.Test]})
-    column_name: Optional[str] = None
-    file_key_name: Optional[str] = None
-    # Was not able to make mypy happy and keep the code working. We need to
-    # refactor the various configs.
-    config: TestConfig = field(default_factory=TestConfig)  # type:ignore
-
-    def same_contents(self, other) -> bool:
-        if other is None:
-            return False
-
-        return self.same_config(other) and self.same_fqn(other) and True
-
-
-CompiledTestNode = Union[CompiledSingularTestNode, CompiledGenericTestNode]
-
-
-PARSED_TYPES: Dict[Type[CompiledNode], Type[ParsedResource]] = {
-    CompiledAnalysisNode: ParsedAnalysisNode,
-    CompiledModelNode: ParsedModelNode,
-    CompiledHookNode: ParsedHookNode,
-    CompiledRPCNode: ParsedRPCNode,
-    CompiledSqlNode: ParsedSqlNode,
-    CompiledSeedNode: ParsedSeedNode,
-    CompiledSnapshotNode: ParsedSnapshotNode,
-    CompiledSingularTestNode: ParsedSingularTestNode,
-    CompiledGenericTestNode: ParsedGenericTestNode,
-}
-
-
-COMPILED_TYPES: Dict[Type[ParsedResource], Type[CompiledNode]] = {
-    ParsedAnalysisNode: CompiledAnalysisNode,
-    ParsedModelNode: CompiledModelNode,
-    ParsedHookNode: CompiledHookNode,
-    ParsedRPCNode: CompiledRPCNode,
-    ParsedSqlNode: CompiledSqlNode,
-    ParsedSeedNode: CompiledSeedNode,
-    ParsedSnapshotNode: CompiledSnapshotNode,
-    ParsedSingularTestNode: CompiledSingularTestNode,
-    ParsedGenericTestNode: CompiledGenericTestNode,
-}
-
-
-# for some types, the compiled type is the parsed type, so make this easy
-CompiledType = Union[Type[CompiledNode], Type[ParsedResource]]
-CompiledResource = Union[ParsedResource, CompiledNode]
-
-
-def compiled_type_for(parsed: ParsedNode) -> CompiledType:
-    if type(parsed) in COMPILED_TYPES:
-        return COMPILED_TYPES[type(parsed)]
-    else:
-        return type(parsed)
-
-
-def parsed_instance_for(compiled: CompiledNode) -> ParsedResource:
-    cls = PARSED_TYPES.get(type(compiled))
-    if cls is None:
-        # how???
-        raise ValueError("invalid resource_type: {}".format(compiled.resource_type))
-
-    return cls.from_dict(compiled.to_dict(omit_none=True))
-
-
-NonSourceCompiledNode = Union[
-    CompiledAnalysisNode,
-    CompiledSingularTestNode,
-    CompiledModelNode,
-    CompiledHookNode,
-    CompiledRPCNode,
-    CompiledSqlNode,
-    CompiledGenericTestNode,
-    CompiledSeedNode,
-    CompiledSnapshotNode,
-]
-
-NonSourceParsedNode = Union[
-    ParsedAnalysisNode,
-    ParsedSingularTestNode,
-    ParsedHookNode,
-    ParsedModelNode,
-    ParsedRPCNode,
-    ParsedSqlNode,
-    ParsedGenericTestNode,
-    ParsedSeedNode,
-    ParsedSnapshotNode,
-]
-
-
-# This is anything that can be in manifest.nodes.
-ManifestNode = Union[
-    NonSourceCompiledNode,
-    NonSourceParsedNode,
-]
-
-# We allow either parsed or compiled nodes, or parsed sources, as some
-# 'compile()' calls in the runner actually just return the original parsed
-# node they were given.
-CompileResultNode = Union[
-    ManifestNode,
-    ParsedSourceDefinition,
-]
-
-# anything that participates in the graph: sources, exposures, metrics,
-# or manifest nodes
-GraphMemberNode = Union[
-    CompileResultNode,
-    ParsedExposure,
-    ParsedMetric,
-]

core/dbt/contracts/graph/manifest.py

@@ -16,44 +16,40 @@ from typing import (
     TypeVar,
     Callable,
     Generic,
-    cast,
     AbstractSet,
     ClassVar,
 )
 from typing_extensions import Protocol
 from uuid import UUID
 
-from dbt.contracts.graph.compiled import (
+from dbt.contracts.graph.nodes import (
-    CompileResultNode,
+    Macro,
-    ManifestNode,
+    Documentation,
-    NonSourceCompiledNode,
+    SourceDefinition,
-    GraphMemberNode,
+    GenericTestNode,
-)
+    Exposure,
-from dbt.contracts.graph.parsed import (
+    Metric,
-    ParsedMacro,
+    Entity,
-    ParsedDocumentation,
-    ParsedSourceDefinition,
-    ParsedGenericTestNode,
-    ParsedExposure,
-    ParsedMetric,
-    HasUniqueID,
     UnpatchedSourceDefinition,
-    ManifestNodes,
+    ManifestNode,
+    GraphMemberNode,
+    ResultNode,
+    BaseNode,
 )
 from dbt.contracts.graph.unparsed import SourcePatch
 from dbt.contracts.files import SourceFile, SchemaSourceFile, FileHash, AnySourceFile
 from dbt.contracts.util import BaseArtifactMetadata, SourceKey, ArtifactMixin, schema_version
 from dbt.dataclass_schema import dbtClassMixin
 from dbt.exceptions import (
-    CompilationException,
+    CompilationError,
-    raise_duplicate_resource_name,
+    DuplicateResourceNameError,
-    raise_compiler_error,
+    DuplicateMacroInPackageError,
+    DuplicateMaterializationNameError,
 )
 from dbt.helper_types import PathSet
 from dbt.events.functions import fire_event
 from dbt.events.types import MergedFromState
 from dbt.node_types import NodeType
-from dbt.ui import line_wrap_message
 from dbt import flags
 from dbt import tracking
 import dbt.utils
@@ -96,7 +92,7 @@ class DocLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_doc(self, doc: ParsedDocumentation):
+    def add_doc(self, doc: Documentation):
         if doc.name not in self.storage:
             self.storage[doc.name] = {}
         self.storage[doc.name][doc.package_name] = doc.unique_id
@@ -105,9 +101,9 @@ class DocLookup(dbtClassMixin):
         for doc in manifest.docs.values():
             self.add_doc(doc)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest) -> ParsedDocumentation:
+    def perform_lookup(self, unique_id: UniqueID, manifest) -> Documentation:
         if unique_id not in manifest.docs:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Doc {unique_id} found in cache but not found in manifest"
             )
         return manifest.docs[unique_id]
@@ -127,7 +123,7 @@ class SourceLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_source(self, source: ParsedSourceDefinition):
+    def add_source(self, source: SourceDefinition):
         if source.search_name not in self.storage:
             self.storage[source.search_name] = {}
 
@@ -138,9 +134,9 @@ class SourceLookup(dbtClassMixin):
             if hasattr(source, "source_name"):
                 self.add_source(source)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedSourceDefinition:
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> SourceDefinition:
         if unique_id not in manifest.sources:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Source {unique_id} found in cache but not found in manifest"
             )
         return manifest.sources[unique_id]
@@ -178,7 +174,7 @@ class RefableLookup(dbtClassMixin):
 
     def perform_lookup(self, unique_id: UniqueID, manifest) -> ManifestNode:
         if unique_id not in manifest.nodes:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Node {unique_id} found in cache but not found in manifest"
             )
         return manifest.nodes[unique_id]
@@ -198,7 +194,7 @@ class MetricLookup(dbtClassMixin):
             return self.perform_lookup(unique_id, manifest)
         return None
 
-    def add_metric(self, metric: ParsedMetric):
+    def add_metric(self, metric: Metric):
         if metric.search_name not in self.storage:
             self.storage[metric.search_name] = {}
 
@@ -209,14 +205,47 @@ class MetricLookup(dbtClassMixin):
             if hasattr(metric, "name"):
                 self.add_metric(metric)
 
-    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> ParsedMetric:
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> Metric:
         if unique_id not in manifest.metrics:
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 f"Metric {unique_id} found in cache but not found in manifest"
             )
         return manifest.metrics[unique_id]
 
 
+class EntityLookup(dbtClassMixin):
+    def __init__(self, manifest: "Manifest"):
+        self.storage: Dict[str, Dict[PackageName, UniqueID]] = {}
+        self.populate(manifest)
+
+    def get_unique_id(self, search_name, package: Optional[PackageName]):
+        return find_unique_id_for_package(self.storage, search_name, package)
+
+    def find(self, search_name, package: Optional[PackageName], manifest: "Manifest"):
+        unique_id = self.get_unique_id(search_name, package)
+        if unique_id is not None:
+            return self.perform_lookup(unique_id, manifest)
+        return None
+
+    def add_entity(self, entity: Entity):
+        if entity.search_name not in self.storage:
+            self.storage[entity.search_name] = {}
+
+        self.storage[entity.search_name][entity.package_name] = entity.unique_id
+
+    def populate(self, manifest):
+        for entity in manifest.entities.values():
+            if hasattr(entity, "name"):
+                self.add_entity(entity)
+
+    def perform_lookup(self, unique_id: UniqueID, manifest: "Manifest") -> Entity:
+        if unique_id not in manifest.entities:
+            raise dbt.exceptions.DbtInternalError(
+                f"Entity {unique_id} found in cache but not found in manifest"
+            )
+        return manifest.entities[unique_id]
+
+
 # This handles both models/seeds/snapshots and sources/metrics/exposures
 class DisabledLookup(dbtClassMixin):
     def __init__(self, manifest: "Manifest"):
@@ -325,7 +354,7 @@ def _sort_values(dct):
 
 
 def build_node_edges(nodes: List[ManifestNode]):
-    """Build the forward and backward edges on the given list of ParsedNodes
+    """Build the forward and backward edges on the given list of ManifestNodes
     and return them as two separate dictionaries, each mapping unique IDs to
     lists of edges.
     """
@@ -343,10 +372,10 @@ def build_node_edges(nodes: List[ManifestNode]):
 # Build a map of children of macros and generic tests
 def build_macro_edges(nodes: List[Any]):
     forward_edges: Dict[str, List[str]] = {
-        n.unique_id: [] for n in nodes if n.unique_id.startswith("macro") or n.depends_on.macros
+        n.unique_id: [] for n in nodes if n.unique_id.startswith("macro") or n.depends_on_macros
     }
     for node in nodes:
-        for unique_id in node.depends_on.macros:
+        for unique_id in node.depends_on_macros:
             if unique_id in forward_edges.keys():
                 forward_edges[unique_id].append(node.unique_id)
     return _sort_values(forward_edges)
@@ -365,7 +394,7 @@ class Locality(enum.IntEnum):
 @dataclass
 class MacroCandidate:
     locality: Locality
-    macro: ParsedMacro
+    macro: Macro
 
     def __eq__(self, other: object) -> bool:
         if not isinstance(other, MacroCandidate):
@@ -403,12 +432,7 @@ class MaterializationCandidate(MacroCandidate):
             return NotImplemented
         equal = self.specificity == other.specificity and self.locality == other.locality
         if equal:
-            raise_compiler_error(
+            raise DuplicateMaterializationNameError(self.macro, other)
-                "Found two materializations with the name {} (packages {} and "
-                "{}). dbt cannot resolve this ambiguity".format(
-                    self.macro.name, self.macro.package_name, other.macro.package_name
-                )
-            )
 
         return equal
 
@@ -430,16 +454,14 @@ M = TypeVar("M", bound=MacroCandidate)
 
 
 class CandidateList(List[M]):
-    def last(self) -> Optional[ParsedMacro]:
+    def last(self) -> Optional[Macro]:
         if not self:
             return None
         self.sort()
         return self[-1].macro
 
 
-def _get_locality(
+def _get_locality(macro: Macro, root_project_name: str, internal_packages: Set[str]) -> Locality:
-    macro: ParsedMacro, root_project_name: str, internal_packages: Set[str]
-) -> Locality:
     if macro.package_name == root_project_name:
         return Locality.Root
     elif macro.package_name in internal_packages:
@@ -465,16 +487,19 @@ class Disabled(Generic[D]):
     target: D
 
 
-MaybeMetricNode = Optional[Union[ParsedMetric, Disabled[ParsedMetric]]]
+MaybeMetricNode = Optional[Union[Metric, Disabled[Metric]]]
 
 
-MaybeDocumentation = Optional[ParsedDocumentation]
+MaybeEntityNode = Optional[Union[Entity, Disabled[Entity]]]
+
+
+MaybeDocumentation = Optional[Documentation]
 
 
 MaybeParsedSource = Optional[
     Union[
-        ParsedSourceDefinition,
+        SourceDefinition,
-        Disabled[ParsedSourceDefinition],
+        Disabled[SourceDefinition],
     ]
 ]
 
@@ -492,14 +517,14 @@ def _update_into(dest: MutableMapping[str, T], new_item: T):
     """
     unique_id = new_item.unique_id
     if unique_id not in dest:
-        raise dbt.exceptions.RuntimeException(
+        raise dbt.exceptions.DbtRuntimeError(
             f"got an update_{new_item.resource_type} call with an "
             f"unrecognized {new_item.resource_type}: {new_item.unique_id}"
         )
     existing = dest[unique_id]
     if new_item.original_file_path != existing.original_file_path:
-        raise dbt.exceptions.RuntimeException(
+        raise dbt.exceptions.DbtRuntimeError(
-            f"cannot update a {new_item.resource_type} to have a new file " f"path!"
+            f"cannot update a {new_item.resource_type} to have a new file path!"
         )
     dest[unique_id] = new_item
 
@@ -514,7 +539,7 @@ class MacroMethods:
 
     def find_macro_by_name(
         self, name: str, root_project_name: str, package: Optional[str]
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         """Find a macro in the graph by its name and package name, or None for
         any package. The root project name is used to determine priority:
          - locally defined macros come first
@@ -537,7 +562,7 @@ class MacroMethods:
 
     def find_generate_macro_by_name(
         self, component: str, root_project_name: str
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         """
         The `generate_X_name` macros are similar to regular ones, but ignore
         imported packages.
@@ -606,11 +631,12 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     # is added it must all be added in the __reduce_ex__ method in the
     # args tuple in the right position.
     nodes: MutableMapping[str, ManifestNode] = field(default_factory=dict)
-    sources: MutableMapping[str, ParsedSourceDefinition] = field(default_factory=dict)
+    sources: MutableMapping[str, SourceDefinition] = field(default_factory=dict)
-    macros: MutableMapping[str, ParsedMacro] = field(default_factory=dict)
+    macros: MutableMapping[str, Macro] = field(default_factory=dict)
-    docs: MutableMapping[str, ParsedDocumentation] = field(default_factory=dict)
+    docs: MutableMapping[str, Documentation] = field(default_factory=dict)
-    exposures: MutableMapping[str, ParsedExposure] = field(default_factory=dict)
+    exposures: MutableMapping[str, Exposure] = field(default_factory=dict)
-    metrics: MutableMapping[str, ParsedMetric] = field(default_factory=dict)
+    metrics: MutableMapping[str, Metric] = field(default_factory=dict)
+    entities: MutableMapping[str, Entity] = field(default_factory=dict)
     selectors: MutableMapping[str, Any] = field(default_factory=dict)
     files: MutableMapping[str, AnySourceFile] = field(default_factory=dict)
     metadata: ManifestMetadata = field(default_factory=ManifestMetadata)
@@ -632,6 +658,9 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
     _metric_lookup: Optional[MetricLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
+    _entity_lookup: Optional[EntityLookup] = field(
+        default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
+    )
     _disabled_lookup: Optional[DisabledLookup] = field(
         default=None, metadata={"serialize": lambda x: None, "deserialize": lambda x: None}
     )
@@ -658,7 +687,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         obj._lock = flags.MP_CONTEXT.Lock()
         return obj
 
-    def sync_update_node(self, new_node: NonSourceCompiledNode) -> NonSourceCompiledNode:
+    def sync_update_node(self, new_node: ManifestNode) -> ManifestNode:
         """update the node with a lock. The only time we should want to lock is
         when compiling an ephemeral ancestor of a node at runtime, because
         multiple threads could be just-in-time compiling the same ephemeral
@@ -671,21 +700,24 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         with self._lock:
             existing = self.nodes[new_node.unique_id]
             if getattr(existing, "compiled", False):
-                # already compiled -> must be a NonSourceCompiledNode
+                # already compiled
-                return cast(NonSourceCompiledNode, existing)
+                return existing
             _update_into(self.nodes, new_node)
             return new_node
 
-    def update_exposure(self, new_exposure: ParsedExposure):
+    def update_exposure(self, new_exposure: Exposure):
         _update_into(self.exposures, new_exposure)
 
-    def update_metric(self, new_metric: ParsedMetric):
+    def update_metric(self, new_metric: Metric):
         _update_into(self.metrics, new_metric)
 
+    def update_entity(self, new_entity: Entity):
+        _update_into(self.entities, new_entity)
+
     def update_node(self, new_node: ManifestNode):
         _update_into(self.nodes, new_node)
 
-    def update_source(self, new_source: ParsedSourceDefinition):
+    def update_source(self, new_source: SourceDefinition):
         _update_into(self.sources, new_source)
 
     def build_flat_graph(self):
@@ -697,6 +729,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.flat_graph = {
             "exposures": {k: v.to_dict(omit_none=False) for k, v in self.exposures.items()},
             "metrics": {k: v.to_dict(omit_none=False) for k, v in self.metrics.items()},
+            "entities": {k: v.to_dict(omit_none=False) for k, v in self.entities.items()},
             "nodes": {k: v.to_dict(omit_none=False) for k, v in self.nodes.items()},
             "sources": {k: v.to_dict(omit_none=False) for k, v in self.sources.items()},
         }
@@ -738,7 +771,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
     def find_materialization_macro_by_name(
         self, project_name: str, materialization_name: str, adapter_type: str
-    ) -> Optional[ParsedMacro]:
+    ) -> Optional[Macro]:
         candidates: CandidateList = CandidateList(
             chain.from_iterable(
                 self._materialization_candidates_for(
@@ -759,6 +792,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.nodes.values(),
             self.sources.values(),
             self.metrics.values(),
+            self.entities.values(),
         )
         for resource in all_resources:
             resource_type_plural = resource.resource_type.pluralize()
@@ -787,6 +821,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             docs={k: _deepcopy(v) for k, v in self.docs.items()},
             exposures={k: _deepcopy(v) for k, v in self.exposures.items()},
             metrics={k: _deepcopy(v) for k, v in self.metrics.items()},
+            entities={k: _deepcopy(v) for k, v in self.entities.items()},
             selectors={k: _deepcopy(v) for k, v in self.selectors.items()},
             metadata=self.metadata,
             disabled={k: _deepcopy(v) for k, v in self.disabled.items()},
@@ -803,6 +838,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 self.sources.values(),
                 self.exposures.values(),
                 self.metrics.values(),
+                self.entities.values(),
             )
         )
         forward_edges, backward_edges = build_node_edges(edge_members)
@@ -828,6 +864,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             docs=self.docs,
             exposures=self.exposures,
             metrics=self.metrics,
+            entities=self.entities,
             selectors=self.selectors,
             metadata=self.metadata,
             disabled=self.disabled,
@@ -849,9 +886,11 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             return self.exposures[unique_id]
         elif unique_id in self.metrics:
             return self.metrics[unique_id]
+        elif unique_id in self.entities:
+            return self.entities[unique_id]
         else:
             # something terrible has happened
-            raise dbt.exceptions.InternalException(
+            raise dbt.exceptions.DbtInternalError(
                 "Expected node {} not found in manifest".format(unique_id)
             )
 
@@ -885,6 +924,12 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self._metric_lookup = MetricLookup(self)
         return self._metric_lookup
 
+    @property
+    def entity_lookup(self) -> EntityLookup:
+        if self._entity_lookup is None:
+            self._entity_lookup = EntityLookup(self)
+        return self._entity_lookup
+
     def rebuild_ref_lookup(self):
         self._ref_lookup = RefableLookup(self)
 
@@ -943,8 +988,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         search_name = f"{target_source_name}.{target_table_name}"
         candidates = _search_packages(current_project, node_package)
 
-        source: Optional[ParsedSourceDefinition] = None
+        source: Optional[SourceDefinition] = None
-        disabled: Optional[List[ParsedSourceDefinition]] = None
+        disabled: Optional[List[SourceDefinition]] = None
 
         for pkg in candidates:
             source = self.source_lookup.find(search_name, pkg, self)
@@ -968,8 +1013,8 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         node_package: str,
     ) -> MaybeMetricNode:
 
-        metric: Optional[ParsedMetric] = None
+        metric: Optional[Metric] = None
-        disabled: Optional[List[ParsedMetric]] = None
+        disabled: Optional[List[Metric]] = None
 
         candidates = _search_packages(current_project, node_package, target_metric_package)
         for pkg in candidates:
@@ -985,6 +1030,31 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             return Disabled(disabled[0])
         return None
 
+    def resolve_entity(
+        self,
+        target_entity_name: str,
+        target_entity_package: Optional[str],
+        current_project: str,
+        node_package: str,
+    ) -> MaybeEntityNode:
+
+        entity: Optional[Entity] = None
+        disabled: Optional[List[Entity]] = None
+
+        candidates = _search_packages(current_project, node_package, target_entity_package)
+        for pkg in candidates:
+            entity = self.entity_lookup.find(target_entity_name, pkg, self)
+
+            if entity is not None and entity.config.enabled:
+                return entity
+
+            # it's possible that the node is disabled
+            if disabled is None:
+                disabled = self.disabled_lookup.find(f"{target_entity_name}", pkg)
+        if disabled:
+            return Disabled(disabled[0])
+        return None
+
     # Called by DocsRuntimeContext.doc
     def resolve_doc(
         self,
@@ -992,7 +1062,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         package: Optional[str],
         current_project: str,
         node_package: str,
-    ) -> Optional[ParsedDocumentation]:
+    ) -> Optional[Documentation]:
         """Resolve the given documentation. This follows the same algorithm as
         resolve_ref except the is_enabled checks are unnecessary as docs are
         always enabled.
@@ -1011,6 +1081,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         adapter,
         other: "WritableManifest",
         selected: AbstractSet[UniqueID],
+        favor_state: bool = False,
     ) -> None:
         """Given the selected unique IDs and a writable manifest, update this
         manifest by replacing any unselected nodes with their counterpart.
@@ -1025,7 +1096,10 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
                 node.resource_type in refables
                 and not node.is_ephemeral
                 and unique_id not in selected
-                and not adapter.get_relation(current.database, current.schema, current.identifier)
+                and (
+                    not adapter.get_relation(current.database, current.schema, current.identifier)
+                    or favor_state
+                )
             ):
                 merged.add(unique_id)
                 self.nodes[unique_id] = node.replace(deferred=True)
@@ -1036,33 +1110,14 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
 
         # log up to 5 items
         sample = list(islice(merged, 5))
-        fire_event(MergedFromState(nbr_merged=len(merged), sample=sample))
+        fire_event(MergedFromState(num_merged=len(merged), sample=sample))
 
     # Methods that were formerly in ParseResult
 
-    def add_macro(self, source_file: SourceFile, macro: ParsedMacro):
+    def add_macro(self, source_file: SourceFile, macro: Macro):
         if macro.unique_id in self.macros:
             # detect that the macro exists and emit an error
-            other_path = self.macros[macro.unique_id].original_file_path
+            raise DuplicateMacroInPackageError(macro=macro, macro_mapping=self.macros)
-            # subtract 2 for the "Compilation Error" indent
-            # note that the line wrap eats newlines, so if you want newlines,
-            # this is the result :(
-            msg = line_wrap_message(
-                f"""\
-                dbt found two macros named "{macro.name}" in the project
-                "{macro.package_name}".
-
-
-                To fix this error, rename or remove one of the following
-                macros:
-
-                    - {macro.original_file_path}
-
-                    - {other_path}
-                """,
-                subtract=2,
-            )
-            raise_compiler_error(msg)
 
         self.macros[macro.unique_id] = macro
         source_file.macros.append(macro.unique_id)
@@ -1082,34 +1137,39 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         self.sources[source.unique_id] = source  # type: ignore
         source_file.sources.append(source.unique_id)
 
-    def add_node_nofile(self, node: ManifestNodes):
+    def add_node_nofile(self, node: ManifestNode):
         # nodes can't be overwritten!
         _check_duplicates(node, self.nodes)
         self.nodes[node.unique_id] = node
 
-    def add_node(self, source_file: AnySourceFile, node: ManifestNodes, test_from=None):
+    def add_node(self, source_file: AnySourceFile, node: ManifestNode, test_from=None):
         self.add_node_nofile(node)
         if isinstance(source_file, SchemaSourceFile):
-            if isinstance(node, ParsedGenericTestNode):
+            if isinstance(node, GenericTestNode):
                 assert test_from
                 source_file.add_test(node.unique_id, test_from)
-            if isinstance(node, ParsedMetric):
+            if isinstance(node, Metric):
                 source_file.metrics.append(node.unique_id)
-            if isinstance(node, ParsedExposure):
+            if isinstance(node, Exposure):
                 source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
-    def add_exposure(self, source_file: SchemaSourceFile, exposure: ParsedExposure):
+    def add_exposure(self, source_file: SchemaSourceFile, exposure: Exposure):
         _check_duplicates(exposure, self.exposures)
         self.exposures[exposure.unique_id] = exposure
         source_file.exposures.append(exposure.unique_id)
 
-    def add_metric(self, source_file: SchemaSourceFile, metric: ParsedMetric):
+    def add_metric(self, source_file: SchemaSourceFile, metric: Metric):
         _check_duplicates(metric, self.metrics)
         self.metrics[metric.unique_id] = metric
         source_file.metrics.append(metric.unique_id)
 
+    def add_entity(self, source_file: SchemaSourceFile, entity: Entity):
+        _check_duplicates(entity, self.entities)
+        self.entities[entity.unique_id] = entity
+        source_file.entities.append(entity.unique_id)
+
     def add_disabled_nofile(self, node: GraphMemberNode):
         # There can be multiple disabled nodes for the same unique_id
         if node.unique_id in self.disabled:
@@ -1117,20 +1177,22 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
         else:
             self.disabled[node.unique_id] = [node]
 
-    def add_disabled(self, source_file: AnySourceFile, node: CompileResultNode, test_from=None):
+    def add_disabled(self, source_file: AnySourceFile, node: ResultNode, test_from=None):
         self.add_disabled_nofile(node)
         if isinstance(source_file, SchemaSourceFile):
-            if isinstance(node, ParsedGenericTestNode):
+            if isinstance(node, GenericTestNode):
                 assert test_from
                 source_file.add_test(node.unique_id, test_from)
-            if isinstance(node, ParsedMetric):
+            if isinstance(node, Metric):
                 source_file.metrics.append(node.unique_id)
-            if isinstance(node, ParsedExposure):
+            if isinstance(node, Entity):
+                source_file.entities.append(node.unique_id)
+            if isinstance(node, Exposure):
                 source_file.exposures.append(node.unique_id)
         else:
             source_file.nodes.append(node.unique_id)
 
-    def add_doc(self, source_file: SourceFile, doc: ParsedDocumentation):
+    def add_doc(self, source_file: SourceFile, doc: Documentation):
         _check_duplicates(doc, self.docs)
         self.docs[doc.unique_id] = doc
         source_file.docs.append(doc.unique_id)
@@ -1152,6 +1214,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self.docs,
             self.exposures,
             self.metrics,
+            self.entities,
             self.selectors,
             self.files,
             self.metadata,
@@ -1164,6 +1227,7 @@ class Manifest(MacroMethods, DataClassMessagePackMixin, dbtClassMixin):
             self._source_lookup,
             self._ref_lookup,
             self._metric_lookup,
+            self._entity_lookup,
             self._disabled_lookup,
             self._analysis_lookup,
         )
@@ -1183,32 +1247,35 @@ AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version("manifest", 7)
+@schema_version("manifest", 8)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
         metadata=dict(description=("The nodes defined in the dbt project and its dependencies"))
     )
-    sources: Mapping[UniqueID, ParsedSourceDefinition] = field(
+    sources: Mapping[UniqueID, SourceDefinition] = field(
         metadata=dict(description=("The sources defined in the dbt project and its dependencies"))
     )
-    macros: Mapping[UniqueID, ParsedMacro] = field(
+    macros: Mapping[UniqueID, Macro] = field(
         metadata=dict(description=("The macros defined in the dbt project and its dependencies"))
     )
-    docs: Mapping[UniqueID, ParsedDocumentation] = field(
+    docs: Mapping[UniqueID, Documentation] = field(
         metadata=dict(description=("The docs defined in the dbt project and its dependencies"))
     )
-    exposures: Mapping[UniqueID, ParsedExposure] = field(
+    exposures: Mapping[UniqueID, Exposure] = field(
         metadata=dict(
             description=("The exposures defined in the dbt project and its dependencies")
         )
     )
-    metrics: Mapping[UniqueID, ParsedMetric] = field(
+    metrics: Mapping[UniqueID, Metric] = field(
         metadata=dict(description=("The metrics defined in the dbt project and its dependencies"))
     )
+    entities: Mapping[UniqueID, Entity] = field(
+        metadata=dict(description=("The entities defined in the dbt project and its dependencies"))
+    )
     selectors: Mapping[UniqueID, Any] = field(
         metadata=dict(description=("The selectors defined in selectors.yml"))
     )
-    disabled: Optional[Mapping[UniqueID, List[CompileResultNode]]] = field(
+    disabled: Optional[Mapping[UniqueID, List[ResultNode]]] = field(
         metadata=dict(description="A mapping of the disabled nodes in the target")
     )
     parent_map: Optional[NodeEdgeMap] = field(
@@ -1229,7 +1296,8 @@ class WritableManifest(ArtifactMixin):
 
     @classmethod
     def compatible_previous_versions(self):
-        return [("manifest", 4), ("manifest", 5), ("manifest", 6)]
+        # return [("manifest", 4), ("manifest", 5), ("manifest", 6), ("manifest", 7)]
+        return []
 
     def __post_serialize__(self, dct):
         for unique_id, node in dct["nodes"].items():
@@ -1238,9 +1306,9 @@ class WritableManifest(ArtifactMixin):
         return dct
 
 
-def _check_duplicates(value: HasUniqueID, src: Mapping[str, HasUniqueID]):
+def _check_duplicates(value: BaseNode, src: Mapping[str, BaseNode]):
     if value.unique_id in src:
-        raise_duplicate_resource_name(value, src[value.unique_id])
+        raise DuplicateResourceNameError(value, src[value.unique_id])
 
 
 K_T = TypeVar("K_T")
@@ -1249,7 +1317,7 @@ V_T = TypeVar("V_T")
 
 def _expect_value(key: K_T, src: Mapping[K_T, V_T], old_file: SourceFile, name: str) -> V_T:
     if key not in src:
-        raise CompilationException(
+        raise CompilationError(
             'Expected to find "{}" in cached "result.{}" based '
             "on cached file information: {}!".format(key, name, old_file)
         )

core/dbt/contracts/graph/metrics.py

@@ -12,7 +12,7 @@ class MetricReference(object):
 
 class ResolvedMetricReference(MetricReference):
     """
-    Simple proxy over a ParsedMetric which delegates property
+    Simple proxy over a Metric which delegates property
     lookups to the underlying node. Also adds helper functions
     for working with metrics (ie. __str__ and templating functions)
     """

core/dbt/contracts/graph/model_config.py

@@ -9,7 +9,7 @@ from dbt.dataclass_schema import (
 )
 from dbt.contracts.graph.unparsed import AdditionalPropertiesAllowed, Docs
 from dbt.contracts.graph.utils import validate_color
-from dbt.exceptions import InternalException, CompilationException
+from dbt.exceptions import DbtInternalError, CompilationError
 from dbt.contracts.util import Replaceable, list_str
 from dbt import hooks
 from dbt.node_types import NodeType
@@ -30,7 +30,7 @@ def _get_meta_value(cls: Type[M], fld: Field, key: str, default: Any) -> M:
     try:
         return cls(value)
     except ValueError as exc:
-        raise InternalException(f"Invalid {cls} value: {value}") from exc
+        raise DbtInternalError(f"Invalid {cls} value: {value}") from exc
 
 
 def _set_meta_value(obj: M, key: str, existing: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
@@ -140,17 +140,17 @@ def _merge_field_value(
         return _listify(self_value) + _listify(other_value)
     elif merge_behavior == MergeBehavior.Update:
         if not isinstance(self_value, dict):
-            raise InternalException(f"expected dict, got {self_value}")
+            raise DbtInternalError(f"expected dict, got {self_value}")
         if not isinstance(other_value, dict):
-            raise InternalException(f"expected dict, got {other_value}")
+            raise DbtInternalError(f"expected dict, got {other_value}")
         value = self_value.copy()
         value.update(other_value)
         return value
     elif merge_behavior == MergeBehavior.DictKeyAppend:
         if not isinstance(self_value, dict):
-            raise InternalException(f"expected dict, got {self_value}")
+            raise DbtInternalError(f"expected dict, got {self_value}")
         if not isinstance(other_value, dict):
-            raise InternalException(f"expected dict, got {other_value}")
+            raise DbtInternalError(f"expected dict, got {other_value}")
         new_dict = {}
         for key in self_value.keys():
             new_dict[key] = _listify(self_value[key])
@@ -172,7 +172,7 @@ def _merge_field_value(
         return new_dict
 
     else:
-        raise InternalException(f"Got an invalid merge_behavior: {merge_behavior}")
+        raise DbtInternalError(f"Got an invalid merge_behavior: {merge_behavior}")
 
 
 def insensitive_patterns(*patterns: str):
@@ -227,7 +227,7 @@ class BaseConfig(AdditionalPropertiesAllowed, Replaceable):
             msg = (
                 'Error, tried to delete config key "{}": Cannot delete ' "built-in keys"
             ).format(key)
-            raise CompilationException(msg)
+            raise CompilationError(msg)
         else:
             del self._extra[key]
 
@@ -368,6 +368,11 @@ class MetricConfig(BaseConfig):
     enabled: bool = True
 
 
+@dataclass
+class EntityConfig(BaseConfig):
+    enabled: bool = True
+
+
 @dataclass
 class ExposureConfig(BaseConfig):
     enabled: bool = True
@@ -495,6 +500,12 @@ class SeedConfig(NodeConfig):
     materialized: str = "seed"
     quote_columns: Optional[bool] = None
 
+    @classmethod
+    def validate(cls, data):
+        super().validate(data)
+        if data.get("materialized") and data.get("materialized") != "seed":
+            raise ValidationError("A seed must have a materialized value of 'seed'")
+
 
 @dataclass
 class TestConfig(NodeAndTestConfig):
@@ -534,6 +545,12 @@ class TestConfig(NodeAndTestConfig):
                     return False
         return True
 
+    @classmethod
+    def validate(cls, data):
+        super().validate(data)
+        if data.get("materialized") and data.get("materialized") != "test":
+            raise ValidationError("A test must have a materialized value of 'test'")
+
 
 @dataclass
 class EmptySnapshotConfig(NodeConfig):
@@ -570,7 +587,6 @@ class SnapshotConfig(EmptySnapshotConfig):
                     f"Invalid value for 'check_cols': {data['check_cols']}. "
                     "Expected 'all' or a list of strings."
                 )
-
         elif data.get("strategy") == "timestamp":
             if not data.get("updated_at"):
                 raise ValidationError(
@@ -582,6 +598,9 @@ class SnapshotConfig(EmptySnapshotConfig):
         # If the strategy is not 'check' or 'timestamp' it's a custom strategy,
         # formerly supported with GenericSnapshotConfig
 
+        if data.get("materialized") and data.get("materialized") != "snapshot":
+            raise ValidationError("A snapshot must have a materialized value of 'snapshot'")
+
     def finalize_and_validate(self):
         data = self.to_dict(omit_none=True)
         self.validate(data)
@@ -590,6 +609,7 @@ class SnapshotConfig(EmptySnapshotConfig):
 
 RESOURCE_TYPES: Dict[NodeType, Type[BaseConfig]] = {
     NodeType.Metric: MetricConfig,
+    NodeType.Entity: EntityConfig,
     NodeType.Exposure: ExposureConfig,
     NodeType.Source: SourceConfig,
     NodeType.Seed: SeedConfig,

core/dbt/contracts/graph/unparsed.py

@@ -11,7 +11,7 @@ from dbt.contracts.util import (
 
 # trigger the PathEncoder
 import dbt.helper_types  # noqa:F401
-from dbt.exceptions import CompilationException, ParsingException
+from dbt.exceptions import CompilationError, ParsingError
 
 from dbt.dataclass_schema import dbtClassMixin, StrEnum, ExtensibleDbtClassMixin, ValidationError
 
@@ -24,7 +24,6 @@ from typing import Optional, List, Union, Dict, Any, Sequence
 @dataclass
 class UnparsedBaseNode(dbtClassMixin, Replaceable):
     package_name: str
-    root_path: str
     path: str
     original_file_path: str
 
@@ -223,7 +222,7 @@ class ExternalPartition(AdditionalPropertiesAllowed, Replaceable):
 
     def __post_init__(self):
         if self.name == "" or self.data_type == "":
-            raise CompilationException("External partition columns must have names and data types")
+            raise CompilationError("External partition columns must have names and data types")
 
 
 @dataclass
@@ -232,7 +231,7 @@ class ExternalTable(AdditionalPropertiesAllowed, Mergeable):
     file_format: Optional[str] = None
     row_format: Optional[str] = None
     tbl_properties: Optional[str] = None
-    partitions: Optional[List[ExternalPartition]] = None
+    partitions: Optional[Union[List[str], List[ExternalPartition]]] = None
 
     def __bool__(self):
         return self.location is not None
@@ -364,7 +363,6 @@ class SourcePatch(dbtClassMixin, Replaceable):
 @dataclass
 class UnparsedDocumentation(dbtClassMixin, Replaceable):
     package_name: str
-    root_path: str
     path: str
     original_file_path: str
 
@@ -486,9 +484,9 @@ class UnparsedMetric(dbtClassMixin, Replaceable):
     name: str
     label: str
     calculation_method: str
-    timestamp: str
     expression: str
     description: str = ""
+    timestamp: Optional[str] = None
     time_grains: List[str] = field(default_factory=list)
     dimensions: List[str] = field(default_factory=list)
     window: Optional[MetricTime] = None
@@ -516,12 +514,40 @@ class UnparsedMetric(dbtClassMixin, Replaceable):
                 errors.append("must contain only letters, numbers and underscores")
 
             if errors:
-                raise ParsingException(
+                raise ParsingError(
                     f"The metric name '{data['name']}' is invalid.  It {', '.join(e for e in errors)}"
                 )
 
+        if data.get("timestamp") is None and data.get("time_grains") is not None:
+            raise ValidationError(
+                f"The metric '{data['name']} has time_grains defined but is missing a timestamp dimension."
+            )
+
+        if data.get("timestamp") is None and data.get("window") is not None:
+            raise ValidationError(
+                f"The metric '{data['name']} has a window defined but is missing a timestamp dimension."
+            )
+
         if data.get("model") is None and data.get("calculation_method") != "derived":
             raise ValidationError("Non-derived metrics require a 'model' property")
 
         if data.get("model") is not None and data.get("calculation_method") == "derived":
             raise ValidationError("Derived metrics cannot have a 'model' property")
+
+
+@dataclass
+class UnparsedEntity(dbtClassMixin, Replaceable):
+    """This class is used for entity information"""
+
+    name: str
+    model: str
+    description: str = ""
+    dimensions: List[str] = field(default_factory=list)
+    meta: Dict[str, Any] = field(default_factory=dict)
+    tags: List[str] = field(default_factory=list)
+    config: Dict[str, Any] = field(default_factory=dict)
+
+    @classmethod
+    def validate(cls, data):
+        super(UnparsedEntity, cls).validate(data)
+        # TODO: Add validation here around include/exclude and others

core/dbt/contracts/project.py

@@ -12,9 +12,7 @@ from dataclasses import dataclass, field
 from typing import Optional, List, Dict, Union, Any
 from mashumaro.types import SerializableType
 
-PIN_PACKAGE_URL = (
+
-    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
-)
 DEFAULT_SEND_ANONYMOUS_USAGE_STATS = True
 
 
@@ -57,6 +55,12 @@ class LocalPackage(Package):
 RawVersion = Union[str, float]
 
 
+@dataclass
+class TarballPackage(Package):
+    tarball: str
+    name: str
+
+
 @dataclass
 class GitPackage(Package):
     git: str
@@ -84,7 +88,7 @@ class RegistryPackage(Package):
             return [str(self.version)]
 
 
-PackageSpec = Union[LocalPackage, GitPackage, RegistryPackage]
+PackageSpec = Union[LocalPackage, TarballPackage, GitPackage, RegistryPackage]
 
 
 @dataclass
@@ -210,6 +214,7 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
     sources: Dict[str, Any] = field(default_factory=dict)
     tests: Dict[str, Any] = field(default_factory=dict)
     metrics: Dict[str, Any] = field(default_factory=dict)
+    entities: Dict[str, Any] = field(default_factory=dict)
     exposures: Dict[str, Any] = field(default_factory=dict)
     vars: Optional[Dict[str, Any]] = field(
         default=None,
@@ -218,7 +223,7 @@ class Project(HyphenatedDbtClassMixin, Replaceable):
         ),
     )
     packages: List[PackageSpec] = field(default_factory=list)
-    query_comment: Optional[Union[QueryComment, NoValue, str]] = NoValue()
+    query_comment: Optional[Union[QueryComment, NoValue, str]] = field(default_factory=NoValue)
 
     @classmethod
     def validate(cls, data):
@@ -245,6 +250,7 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
     printer_width: Optional[int] = None
     write_json: Optional[bool] = None
     warn_error: Optional[bool] = None
+    warn_error_options: Optional[Dict[str, Union[str, List[str]]]] = None
     log_format: Optional[str] = None
     debug: Optional[bool] = None
     version_check: Optional[bool] = None
@@ -253,7 +259,6 @@ class UserConfig(ExtensibleDbtClassMixin, Replaceable, UserConfigContract):
     static_parser: Optional[bool] = None
     indirect_selection: Optional[str] = None
     cache_selected_only: Optional[bool] = None
-    event_buffer_size: Optional[int] = None
 
 
 @dataclass

core/dbt/contracts/relation.py

@@ -9,7 +9,7 @@ from typing_extensions import Protocol
 from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
 from dbt.contracts.util import Replaceable
-from dbt.exceptions import raise_dataclass_not_dict, CompilationException
+from dbt.exceptions import CompilationError, DataclassNotDictError
 from dbt.utils import deep_merge
 
 
@@ -43,10 +43,10 @@ class FakeAPIObject(dbtClassMixin, Replaceable, Mapping):
             raise KeyError(key) from None
 
     def __iter__(self):
-        raise_dataclass_not_dict(self)
+        raise DataclassNotDictError(self)
 
     def __len__(self):
-        raise_dataclass_not_dict(self)
+        raise DataclassNotDictError(self)
 
     def incorporate(self, **kwargs):
         value = self.to_dict(omit_none=True)
@@ -88,13 +88,11 @@ class Path(FakeAPIObject):
     def __post_init__(self):
         # handle pesky jinja2.Undefined sneaking in here and messing up rende
         if not isinstance(self.database, (type(None), str)):
-            raise CompilationException("Got an invalid path database: {}".format(self.database))
+            raise CompilationError("Got an invalid path database: {}".format(self.database))
         if not isinstance(self.schema, (type(None), str)):
-            raise CompilationException("Got an invalid path schema: {}".format(self.schema))
+            raise CompilationError("Got an invalid path schema: {}".format(self.schema))
         if not isinstance(self.identifier, (type(None), str)):
-            raise CompilationException(
+            raise CompilationError("Got an invalid path identifier: {}".format(self.identifier))
-                "Got an invalid path identifier: {}".format(self.identifier)
-            )
 
     def get_lowered_part(self, key: ComponentName) -> Optional[str]:
         part = self.get_part(key)

core/dbt/contracts/results.py

@@ -1,6 +1,5 @@
-from dbt.contracts.graph.manifest import CompileResultNode
 from dbt.contracts.graph.unparsed import FreshnessThreshold
-from dbt.contracts.graph.parsed import ParsedSourceDefinition
+from dbt.contracts.graph.nodes import SourceDefinition, ResultNode
 from dbt.contracts.util import (
     BaseArtifactMetadata,
     ArtifactMixin,
@@ -8,14 +7,13 @@ from dbt.contracts.util import (
     Replaceable,
     schema_version,
 )
-from dbt.exceptions import InternalException
+from dbt.exceptions import DbtInternalError
 from dbt.events.functions import fire_event
 from dbt.events.types import TimingInfoCollected
-from dbt.logger import (
+from dbt.events.proto_types import RunResultMsg, TimingInfoMsg
-    TimingProcessor,
+from dbt.events.contextvars import get_node_info
-    JsonOnly,
+from dbt.logger import TimingProcessor
-)
+from dbt.utils import lowercase, cast_to_str, cast_to_int
-from dbt.utils import lowercase
 from dbt.dataclass_schema import dbtClassMixin, StrEnum
 
 import agate
@@ -47,7 +45,14 @@ class TimingInfo(dbtClassMixin):
     def end(self):
         self.completed_at = datetime.utcnow()
 
+    def to_msg(self):
+        timsg = TimingInfoMsg(
+            name=self.name, started_at=self.started_at, completed_at=self.completed_at
+        )
+        return timsg
 
+
+# This is a context manager
 class collect_timing_info:
     def __init__(self, name: str):
         self.timing_info = TimingInfo(name=name)
@@ -58,8 +63,13 @@ class collect_timing_info:
 
     def __exit__(self, exc_type, exc_value, traceback):
         self.timing_info.end()
-        with JsonOnly(), TimingProcessor(self.timing_info):
+        # Note: when legacy logger is removed, we can remove the following line
-            fire_event(TimingInfoCollected())
+        with TimingProcessor(self.timing_info):
+            fire_event(
+                TimingInfoCollected(
+                    timing_info=self.timing_info.to_msg(), node_info=get_node_info()
+                )
+            )
 
 
 class RunningStatus(StrEnum):
@@ -119,10 +129,22 @@ class BaseResult(dbtClassMixin):
             data["failures"] = None
         return data
 
+    def to_msg(self):
+        # TODO: add more fields
+        msg = RunResultMsg()
+        msg.status = str(self.status)
+        msg.message = cast_to_str(self.message)
+        msg.thread = self.thread_id
+        msg.execution_time = self.execution_time
+        msg.num_failures = cast_to_int(self.failures)
+        msg.timing_info = [ti.to_msg() for ti in self.timing]
+        # adapter_response
+        return msg
+
 
 @dataclass
 class NodeResult(BaseResult):
-    node: CompileResultNode
+    node: ResultNode
 
 
 @dataclass
@@ -208,7 +230,9 @@ class RunResultsArtifact(ExecutionResult, ArtifactMixin):
         generated_at: datetime,
         args: Dict,
     ):
-        processed_results = [process_run_result(result) for result in results]
+        processed_results = [
+            process_run_result(result) for result in results if isinstance(result, RunResult)
+        ]
         meta = RunResultsMetadata(
             dbt_schema_version=str(cls.dbt_schema_version),
             generated_at=generated_at,
@@ -259,7 +283,7 @@ class RunOperationResultsArtifact(RunOperationResult, ArtifactMixin):
 
 @dataclass
 class SourceFreshnessResult(NodeResult):
-    node: ParsedSourceDefinition
+    node: SourceDefinition
     status: FreshnessStatus
     max_loaded_at: datetime
     snapshotted_at: datetime
@@ -319,15 +343,15 @@ def process_freshness_result(result: FreshnessNodeResult) -> FreshnessNodeOutput
 
     # we know that this must be a SourceFreshnessResult
     if not isinstance(result, SourceFreshnessResult):
-        raise InternalException(
+        raise DbtInternalError(
             "Got {} instead of a SourceFreshnessResult for a "
             "non-error result in freshness execution!".format(type(result))
         )
     # if we're here, we must have a non-None freshness threshold
     criteria = result.node.freshness
     if criteria is None:
-        raise InternalException(
+        raise DbtInternalError(
-            "Somehow evaluated a freshness result for a source " "that has no freshness criteria!"
+            "Somehow evaluated a freshness result for a source that has no freshness criteria!"
         )
     return SourceFreshnessOutput(
         unique_id=unique_id,

core/dbt/contracts/sql.py

@@ -5,7 +5,7 @@ from typing import Optional, List, Any, Dict, Sequence
 
 from dbt.dataclass_schema import dbtClassMixin
 
-from dbt.contracts.graph.compiled import CompileResultNode
+from dbt.contracts.graph.nodes import ResultNode
 from dbt.contracts.results import (
     RunResult,
     RunResultsArtifact,
@@ -32,7 +32,7 @@ class RemoteResult(VersionedSchema):
 class RemoteCompileResultMixin(RemoteResult):
     raw_code: str
     compiled_code: str
-    node: CompileResultNode
+    node: ResultNode
     timing: List[TimingInfo]
 
 

core/dbt/contracts/state.py

@@ -3,7 +3,7 @@ from .graph.manifest import WritableManifest
 from .results import RunResultsArtifact
 from .results import FreshnessExecutionResultArtifact
 from typing import Optional
-from dbt.exceptions import IncompatibleSchemaException
+from dbt.exceptions import IncompatibleSchemaError
 
 
 class PreviousState:
@@ -19,7 +19,7 @@ class PreviousState:
         if manifest_path.exists() and manifest_path.is_file():
             try:
                 self.manifest = WritableManifest.read_and_check_versions(str(manifest_path))
-            except IncompatibleSchemaException as exc:
+            except IncompatibleSchemaError as exc:
                 exc.add_filename(str(manifest_path))
                 raise
 
@@ -27,7 +27,7 @@ class PreviousState:
         if results_path.exists() and results_path.is_file():
             try:
                 self.results = RunResultsArtifact.read_and_check_versions(str(results_path))
-            except IncompatibleSchemaException as exc:
+            except IncompatibleSchemaError as exc:
                 exc.add_filename(str(results_path))
                 raise
 
@@ -37,7 +37,7 @@ class PreviousState:
                 self.sources = FreshnessExecutionResultArtifact.read_and_check_versions(
                     str(sources_path)
                 )
-            except IncompatibleSchemaException as exc:
+            except IncompatibleSchemaError as exc:
                 exc.add_filename(str(sources_path))
                 raise
 
@@ -47,6 +47,6 @@ class PreviousState:
                 self.sources_current = FreshnessExecutionResultArtifact.read_and_check_versions(
                     str(sources_current_path)
                 )
-            except IncompatibleSchemaException as exc:
+            except IncompatibleSchemaError as exc:
                 exc.add_filename(str(sources_current_path))
                 raise

core/dbt/contracts/util.py

@@ -1,17 +1,16 @@
 import dataclasses
-import os
 from datetime import datetime
 from typing import List, Tuple, ClassVar, Type, TypeVar, Dict, Any, Optional
 
 from dbt.clients.system import write_json, read_json
 from dbt import deprecations
 from dbt.exceptions import (
-    InternalException,
+    DbtInternalError,
-    RuntimeException,
+    DbtRuntimeError,
-    IncompatibleSchemaException,
+    IncompatibleSchemaError,
 )
 from dbt.version import __version__
-from dbt.events.functions import get_invocation_id
+from dbt.events.functions import get_invocation_id, get_metadata_vars
 from dbt.dataclass_schema import dbtClassMixin
 
 from dbt.dataclass_schema import (
@@ -124,7 +123,7 @@ class Readable:
         try:
             data = read_json(path)
         except (EnvironmentError, ValueError) as exc:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f'Could not read {cls.__name__} at "{path}" as JSON: {exc}'
             ) from exc
 
@@ -148,20 +147,6 @@ class SchemaVersion:
         return BASE_SCHEMAS_URL + self.path
 
 
-SCHEMA_VERSION_KEY = "dbt_schema_version"
-
-
-METADATA_ENV_PREFIX = "DBT_ENV_CUSTOM_ENV_"
-
-
-def get_metadata_env() -> Dict[str, str]:
-    return {
-        k[len(METADATA_ENV_PREFIX) :]: v
-        for k, v in os.environ.items()
-        if k.startswith(METADATA_ENV_PREFIX)
-    }
-
-
 # This is used in the ManifestMetadata, RunResultsMetadata, RunOperationResultMetadata,
 # FreshnessMetadata, and CatalogMetadata classes
 @dataclasses.dataclass
@@ -170,7 +155,7 @@ class BaseArtifactMetadata(dbtClassMixin):
     dbt_version: str = __version__
     generated_at: datetime = dataclasses.field(default_factory=datetime.utcnow)
     invocation_id: Optional[str] = dataclasses.field(default_factory=get_invocation_id)
-    env: Dict[str, str] = dataclasses.field(default_factory=get_metadata_env)
+    env: Dict[str, str] = dataclasses.field(default_factory=get_metadata_vars)
 
     def __post_serialize__(self, dct):
         dct = super().__post_serialize__(dct)
@@ -252,16 +237,61 @@ def rename_sql_attr(node_content: dict) -> dict:
     return node_content
 
 
+def upgrade_node_content(node_content):
+    rename_sql_attr(node_content)
+    if node_content["resource_type"] != "seed" and "root_path" in node_content:
+        del node_content["root_path"]
+
+
+def upgrade_seed_content(node_content):
+    # Remove compilation related attributes
+    for attr_name in (
+        "language",
+        "refs",
+        "sources",
+        "metrics",
+        "depends_on",
+        "compiled_path",
+        "compiled",
+        "compiled_code",
+        "extra_ctes_injected",
+        "extra_ctes",
+        "relation_name",
+    ):
+        if attr_name in node_content:
+            del node_content[attr_name]
+
+
 def upgrade_manifest_json(manifest: dict) -> dict:
     for node_content in manifest.get("nodes", {}).values():
-        node_content = rename_sql_attr(node_content)
+        upgrade_node_content(node_content)
+        if node_content["resource_type"] == "seed":
+            upgrade_seed_content(node_content)
     for disabled in manifest.get("disabled", {}).values():
         # There can be multiple disabled nodes for the same unique_id
         # so make sure all the nodes get the attr renamed
-        disabled = [rename_sql_attr(n) for n in disabled]
+        for node_content in disabled:
+            upgrade_node_content(node_content)
+            if node_content["resource_type"] == "seed":
+                upgrade_seed_content(node_content)
     for metric_content in manifest.get("metrics", {}).values():
         # handle attr renames + value translation ("expression" -> "derived")
         metric_content = rename_metric_attr(metric_content)
+        if "root_path" in metric_content:
+            del metric_content["root_path"]
+    for exposure_content in manifest.get("exposures", {}).values():
+        if "root_path" in exposure_content:
+            del exposure_content["root_path"]
+    for source_content in manifest.get("sources", {}).values():
+        if "root_path" in exposure_content:
+            del source_content["root_path"]
+    for macro_content in manifest.get("macros", {}).values():
+        if "root_path" in macro_content:
+            del macro_content["root_path"]
+    for doc_content in manifest.get("docs", {}).values():
+        if "root_path" in doc_content:
+            del doc_content["root_path"]
+        doc_content["resource_type"] = "doc"
     return manifest
 
 
@@ -290,7 +320,7 @@ class VersionedSchema(dbtClassMixin):
         try:
             data = read_json(path)
         except (EnvironmentError, ValueError) as exc:
-            raise RuntimeException(
+            raise DbtRuntimeError(
                 f'Could not read {cls.__name__} at "{path}" as JSON: {exc}'
             ) from exc
 
@@ -302,11 +332,11 @@ class VersionedSchema(dbtClassMixin):
                 previous_schema_version = data["metadata"]["dbt_schema_version"]
                 # cls.dbt_schema_version is a SchemaVersion object
                 if not cls.is_compatible_version(previous_schema_version):
-                    raise IncompatibleSchemaException(
+                    raise IncompatibleSchemaError(
                         expected=str(cls.dbt_schema_version),
                         found=previous_schema_version,
                     )
-        if get_manifest_schema_version(data) <= 6:
+        if get_manifest_schema_version(data) <= 7:
             data = upgrade_manifest_json(data)
         return cls.from_dict(data)  # type: ignore
 
@@ -327,7 +357,7 @@ class ArtifactMixin(VersionedSchema, Writable, Readable):
     def validate(cls, data):
         super().validate(data)
         if cls.dbt_schema_version is None:
-            raise InternalException("Cannot call from_dict with no schema version!")
+            raise DbtInternalError("Cannot call from_dict with no schema version!")
 
 
 class Identifier(ValidatedStringMixin):

core/dbt/deprecations.py

@@ -1,14 +1,14 @@
+import abc
 from typing import Optional, Set, List, Dict, ClassVar
 
 import dbt.exceptions
-from dbt import ui
 
 import dbt.tracking
 
 
 class DBTDeprecation:
     _name: ClassVar[Optional[str]] = None
-    _description: ClassVar[Optional[str]] = None
+    _event: ClassVar[Optional[str]] = None
 
     @property
     def name(self) -> str:
@@ -21,66 +21,50 @@ class DBTDeprecation:
             dbt.tracking.track_deprecation_warn({"deprecation_name": self.name})
 
     @property
-    def description(self) -> str:
+    def event(self) -> abc.ABCMeta:
-        if self._description is not None:
+        if self._event is not None:
-            return self._description
+            module_path = dbt.events.types
-        raise NotImplementedError("description not implemented for {}".format(self))
+            class_name = self._event
+
+            try:
+                return getattr(module_path, class_name)
+            except AttributeError:
+                msg = f"Event Class `{class_name}` is not defined in `{module_path}`"
+                raise NameError(msg)
+        raise NotImplementedError("event not implemented for {}".format(self._event))
 
     def show(self, *args, **kwargs) -> None:
         if self.name not in active_deprecations:
-            desc = self.description.format(**kwargs)
+            event = self.event(**kwargs)
-            msg = ui.line_wrap_message(desc, prefix="Deprecated functionality\n\n")
+            dbt.events.functions.warn_or_error(event)
-            dbt.exceptions.warn_or_error(msg, log_fmt=ui.warning_tag("{}"))
             self.track_deprecation_warn()
             active_deprecations.add(self.name)
 
 
 class PackageRedirectDeprecation(DBTDeprecation):
     _name = "package-redirect"
-    _description = """\
+    _event = "PackageRedirectDeprecation"
-    The `{old_name}` package is deprecated in favor of `{new_name}`. Please update
-    your `packages.yml` configuration to use `{new_name}` instead.
-    """
 
 
 class PackageInstallPathDeprecation(DBTDeprecation):
     _name = "install-packages-path"
-    _description = """\
+    _event = "PackageInstallPathDeprecation"
-    The default package install path has changed from `dbt_modules` to `dbt_packages`.
-    Please update `clean-targets` in `dbt_project.yml` and check `.gitignore` as well.
-    Or, set `packages-install-path: dbt_modules` if you'd like to keep the current value.
-    """
 
 
-class ConfigPathDeprecation(DBTDeprecation):
+class ConfigSourcePathDeprecation(DBTDeprecation):
-    _description = """\
-    The `{deprecated_path}` config has been renamed to `{exp_path}`.
-    Please update your `dbt_project.yml` configuration to reflect this change.
-    """
-
-
-class ConfigSourcePathDeprecation(ConfigPathDeprecation):
     _name = "project-config-source-paths"
+    _event = "ConfigSourcePathDeprecation"
 
 
-class ConfigDataPathDeprecation(ConfigPathDeprecation):
+class ConfigDataPathDeprecation(DBTDeprecation):
     _name = "project-config-data-paths"
-
+    _event = "ConfigDataPathDeprecation"
-
-_adapter_renamed_description = """\
-The adapter function `adapter.{old_name}` is deprecated and will be removed in
-a future release of dbt. Please use `adapter.{new_name}` instead.
-
-Documentation for {new_name} can be found here:
-
-    https://docs.getdbt.com/docs/adapter
-"""
 
 
 def renamed_method(old_name: str, new_name: str):
     class AdapterDeprecationWarning(DBTDeprecation):
         _name = "adapter:{}".format(old_name)
-        _description = _adapter_renamed_description.format(old_name=old_name, new_name=new_name)
+        _event = "AdapterDeprecationWarning"
 
     dep = AdapterDeprecationWarning()
     deprecations_list.append(dep)
@@ -89,26 +73,12 @@ def renamed_method(old_name: str, new_name: str):
 
 class MetricAttributesRenamed(DBTDeprecation):
     _name = "metric-attr-renamed"
-    _description = """\
+    _event = "MetricAttributesRenamed"
-dbt-core v1.3 renamed attributes for metrics:
-\n  'sql'              -> 'expression'
-\n  'type'             -> 'calculation_method'
-\n  'type: expression' -> 'calculation_method: derived'
-\nThe old metric parameter names will be fully deprecated in v1.4.
-\nPlease remove them from the metric definition of metric '{metric_name}'
-\nRelevant issue here: https://github.com/dbt-labs/dbt-core/issues/5849
-"""
 
 
 class ExposureNameDeprecation(DBTDeprecation):
     _name = "exposure-name"
-    _description = """\
+    _event = "ExposureNameDeprecation"
-    Starting in v1.3, the 'name' of an exposure should contain only letters, numbers, and underscores.
-    Exposures support a new property, 'label', which may contain spaces, capital letters, and special characters.
-    {exposure} does not follow this pattern.
-    Please update the 'name', and use the 'label' property for a human-friendly title.
-    This will raise an error in a future version of dbt-core.
-    """
 
 
 def warn(name, *args, **kwargs):
@@ -125,12 +95,12 @@ def warn(name, *args, **kwargs):
 active_deprecations: Set[str] = set()
 
 deprecations_list: List[DBTDeprecation] = [
-    ExposureNameDeprecation(),
+    PackageRedirectDeprecation(),
+    PackageInstallPathDeprecation(),
     ConfigSourcePathDeprecation(),
     ConfigDataPathDeprecation(),
-    PackageInstallPathDeprecation(),
-    PackageRedirectDeprecation(),
     MetricAttributesRenamed(),
+    ExposureNameDeprecation(),
 ]
 
 deprecations: Dict[str, DBTDeprecation] = {d.name: d for d in deprecations_list}

core/dbt/deps/README.md

@@ -16,6 +16,8 @@ Defines the base classes of `PinnedPackage` and `UnpinnedPackage`.
 
 `downloads_directory` sets the directory packages will be downloaded to.
 
+`_install` has retry logic if the download or untarring process hit exceptions (see `dbt.utils._connection_exception_retry`).
+
 ## `git.py`
 
 Extends `PinnedPackage` and `UnpinnedPackage` specific to dbt packages defined with git urls.
@@ -28,8 +30,10 @@ Extends `PinnedPackage` and `UnpinnedPackage` specific to dbt packages defined l
 
 Extends `PinnedPackage` and `UnpinnedPackage` specific to dbt packages defined on the dbt Hub registry.
 
-`install` has retry logic if the download or untarring process hit exceptions (see `dbt.utils._connection_exception_retry`).
 
 ## `resolver.py`
 
 Resolves the package definition into package objects to download.
+
+## `tarball.py`
+Extends `PinnedPackage` and `UnpinnedPackage` specific to dbt packages defined by a URL to a tarball hosted on an HTTP server.

core/dbt/deps/base.py

@@ -1,13 +1,16 @@
 import abc
 import os
+import functools
 import tempfile
 from contextlib import contextmanager
+from pathlib import Path
 from typing import List, Optional, Generic, TypeVar
 
 from dbt.clients import system
 from dbt.contracts.project import ProjectPackageMetadata
 from dbt.events.functions import fire_event
 from dbt.events.types import DepsSetDownloadDirectory
+from dbt.utils import _connection_exception_retry as connection_exception_retry
 
 DOWNLOADS_PATH = None
 
@@ -74,7 +77,7 @@ class PinnedPackage(BasePackage):
         raise NotImplementedError
 
     @abc.abstractmethod
-    def install(self, project):
+    def install(self, project, renderer):
         raise NotImplementedError
 
     @abc.abstractmethod
@@ -97,6 +100,34 @@ class PinnedPackage(BasePackage):
     def get_subdirectory(self):
         return None
 
+    def _install(self, project, renderer):
+        metadata = self.fetch_metadata(project, renderer)
+
+        tar_name = f"{self.package}.{self.version}.tar.gz"
+        tar_path = (Path(get_downloads_path()) / tar_name).resolve(strict=False)
+        system.make_directory(str(tar_path.parent))
+
+        download_url = metadata.downloads.tarball
+        deps_path = project.packages_install_path
+        package_name = self.get_project_name(project, renderer)
+
+        download_untar_fn = functools.partial(
+            self.download_and_untar, download_url, str(tar_path), deps_path, package_name
+        )
+        connection_exception_retry(download_untar_fn, 5)
+
+    def download_and_untar(self, download_url, tar_path, deps_path, package_name):
+        """
+        Sometimes the download of the files fails and we want to retry.  Sometimes the
+        download appears successful but the file did not make it through as expected
+        (generally due to a github incident).  Either way we want to retry downloading
+        and untarring to see if we can get a success.  Call this within
+        `_connection_exception_retry`
+        """
+
+        system.download(download_url, tar_path)
+        system.untar_package(tar_path, deps_path, package_name)
+
 
 SomePinned = TypeVar("SomePinned", bound=PinnedPackage)
 SomeUnpinned = TypeVar("SomeUnpinned", bound="UnpinnedPackage")

core/dbt/deps/git.py

@@ -9,14 +9,9 @@ from dbt.contracts.project import (
     GitPackage,
 )
 from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
-from dbt.exceptions import ExecutableError, warn_or_error, raise_dependency_error
+from dbt.exceptions import ExecutableError, MultipleVersionGitDepsError
-from dbt.events.functions import fire_event
+from dbt.events.functions import fire_event, warn_or_error
-from dbt.events.types import EnsureGitInstalled
+from dbt.events.types import EnsureGitInstalled, DepsUnpinned
-from dbt import ui
-
-PIN_PACKAGE_URL = (
-    "https://docs.getdbt.com/docs/package-management#section-specifying-package-versions"  # noqa
-)
 
 
 def md5sum(s: str):
@@ -62,14 +57,6 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
         else:
             return "revision {}".format(self.revision)
 
-    def unpinned_msg(self):
-        if self.revision == "HEAD":
-            return "not pinned, using HEAD (default branch)"
-        elif self.revision in ("main", "master"):
-            return f'pinned to the "{self.revision}" branch'
-        else:
-            return None
-
     def _checkout(self):
         """Performs a shallow clone of the repository into the downloads
         directory. This function can be called repeatedly. If the project has
@@ -92,14 +79,8 @@ class GitPinnedPackage(GitPackageMixin, PinnedPackage):
     def _fetch_metadata(self, project, renderer) -> ProjectPackageMetadata:
         path = self._checkout()
 
-        if self.unpinned_msg() and self.warn_unpinned:
+        if (self.revision == "HEAD" or self.revision in ("main", "master")) and self.warn_unpinned:
-            warn_or_error(
+            warn_or_error(DepsUnpinned(git=self.git))
-                'The git package "{}" \n\tis {}.\n\tThis can introduce '
-                "breaking changes into your project without warning!\n\nSee {}".format(
-                    self.git, self.unpinned_msg(), PIN_PACKAGE_URL
-                ),
-                log_fmt=ui.yellow("WARNING: {}"),
-            )
         loaded = Project.from_project_root(path, renderer)
         return ProjectPackageMetadata.from_project(loaded)
 
@@ -162,10 +143,7 @@ class GitUnpinnedPackage(GitPackageMixin, UnpinnedPackage[GitPinnedPackage]):
         if len(requested) == 0:
             requested = {"HEAD"}
         elif len(requested) > 1:
-            raise_dependency_error(
+            raise MultipleVersionGitDepsError(self.git, requested)
-                "git dependencies should contain exactly one version. "
-                "{} contains: {}".format(self.git, requested)
-            )
 
         return GitPinnedPackage(
             git=self.git,

core/dbt/deps/registry.py

@@ -1,23 +1,20 @@
-import os
-import functools
 from typing import List
 
 from dbt import semver
 from dbt import flags
 from dbt.version import get_installed_version
-from dbt.clients import registry, system
+from dbt.clients import registry
 from dbt.contracts.project import (
     RegistryPackageMetadata,
     RegistryPackage,
 )
-from dbt.deps.base import PinnedPackage, UnpinnedPackage, get_downloads_path
+from dbt.deps.base import PinnedPackage, UnpinnedPackage
 from dbt.exceptions import (
-    package_version_not_found,
+    DependencyError,
-    VersionsNotCompatibleException,
+    PackageNotFoundError,
-    DependencyException,
+    PackageVersionNotFoundError,
-    package_not_found,
+    VersionsNotCompatibleError,
 )
-from dbt.utils import _connection_exception_retry as connection_exception_retry
 
 
 class RegistryPackageMixin:
@@ -60,32 +57,7 @@ class RegistryPinnedPackage(RegistryPackageMixin, PinnedPackage):
         return RegistryPackageMetadata.from_dict(dct)
 
     def install(self, project, renderer):
-        metadata = self.fetch_metadata(project, renderer)
+        self._install(project, renderer)
-
-        tar_name = "{}.{}.tar.gz".format(self.package, self.version)
-        tar_path = os.path.realpath(os.path.join(get_downloads_path(), tar_name))
-        system.make_directory(os.path.dirname(tar_path))
-
-        download_url = metadata.downloads.tarball
-        deps_path = project.packages_install_path
-        package_name = self.get_project_name(project, renderer)
-
-        download_untar_fn = functools.partial(
-            self.download_and_untar, download_url, tar_path, deps_path, package_name
-        )
-        connection_exception_retry(download_untar_fn, 5)
-
-    def download_and_untar(self, download_url, tar_path, deps_path, package_name):
-        """
-        Sometimes the download of the files fails and we want to retry.  Sometimes the
-        download appears successful but the file did not make it through as expected
-        (generally due to a github incident).  Either way we want to retry downloading
-        and untarring to see if we can get a success.  Call this within
-        `_connection_exception_retry`
-        """
-
-        system.download(download_url, tar_path)
-        system.untar_package(tar_path, deps_path, package_name)
 
 
 class RegistryUnpinnedPackage(RegistryPackageMixin, UnpinnedPackage[RegistryPinnedPackage]):
@@ -99,7 +71,7 @@ class RegistryUnpinnedPackage(RegistryPackageMixin, UnpinnedPackage[RegistryPinn
     def _check_in_index(self):
         index = registry.index_cached()
         if self.package not in index:
-            package_not_found(self.package)
+            raise PackageNotFoundError(self.package)
 
     @classmethod
     def from_contract(cls, contract: RegistryPackage) -> "RegistryUnpinnedPackage":
@@ -123,9 +95,9 @@ class RegistryUnpinnedPackage(RegistryPackageMixin, UnpinnedPackage[RegistryPinn
         self._check_in_index()
         try:
             range_ = semver.reduce_versions(*self.versions)
-        except VersionsNotCompatibleException as e:
+        except VersionsNotCompatibleError as e:
             new_msg = "Version error for package {}: {}".format(self.name, e)
-            raise DependencyException(new_msg) from e
+            raise DependencyError(new_msg) from e
 
         should_version_check = bool(flags.VERSION_CHECK)
         dbt_version = get_installed_version()
@@ -146,7 +118,9 @@ class RegistryUnpinnedPackage(RegistryPackageMixin, UnpinnedPackage[RegistryPinn
             target = None
         if not target:
             # raise an exception if no installable target version is found
-            package_version_not_found(self.package, range_, installable, should_version_check)
+            raise PackageVersionNotFoundError(
+                self.package, range_, installable, should_version_check
+            )
         latest_compatible = installable[-1]
         return RegistryPinnedPackage(
             package=self.package, version=target, version_latest=latest_compatible

core/dbt/deps/resolver.py

@@ -1,22 +1,29 @@
 from dataclasses import dataclass, field
 from typing import Dict, List, NoReturn, Union, Type, Iterator, Set
 
-from dbt.exceptions import raise_dependency_error, InternalException
+from dbt.exceptions import (
+    DuplicateDependencyToRootError,
+    DuplicateProjectDependencyError,
+    MismatchedDependencyTypeError,
+    DbtInternalError,
+)
 
 from dbt.config import Project, RuntimeConfig
 from dbt.config.renderer import DbtProjectYamlRenderer
 from dbt.deps.base import BasePackage, PinnedPackage, UnpinnedPackage
 from dbt.deps.local import LocalUnpinnedPackage
+from dbt.deps.tarball import TarballUnpinnedPackage
 from dbt.deps.git import GitUnpinnedPackage
 from dbt.deps.registry import RegistryUnpinnedPackage
 
 from dbt.contracts.project import (
     LocalPackage,
+    TarballPackage,
     GitPackage,
     RegistryPackage,
 )
 
-PackageContract = Union[LocalPackage, GitPackage, RegistryPackage]
+PackageContract = Union[LocalPackage, TarballPackage, GitPackage, RegistryPackage]
 
 
 @dataclass
@@ -49,10 +56,7 @@ class PackageListing:
         self.packages[key_str] = value
 
     def _mismatched_types(self, old: UnpinnedPackage, new: UnpinnedPackage) -> NoReturn:
-        raise_dependency_error(
+        raise MismatchedDependencyTypeError(new, old)
-            f"Cannot incorporate {new} ({new.__class__.__name__}) in {old} "
-            f"({old.__class__.__name__}): mismatched types"
-        )
 
     def incorporate(self, package: UnpinnedPackage):
         key: str = self._pick_key(package)
@@ -69,12 +73,14 @@ class PackageListing:
         for contract in src:
             if isinstance(contract, LocalPackage):
                 pkg = LocalUnpinnedPackage.from_contract(contract)
+            elif isinstance(contract, TarballPackage):
+                pkg = TarballUnpinnedPackage.from_contract(contract)
             elif isinstance(contract, GitPackage):
                 pkg = GitUnpinnedPackage.from_contract(contract)
             elif isinstance(contract, RegistryPackage):
                 pkg = RegistryUnpinnedPackage.from_contract(contract)
             else:
-                raise InternalException("Invalid package type {}".format(type(contract)))
+                raise DbtInternalError("Invalid package type {}".format(type(contract)))
             self.incorporate(pkg)
 
     @classmethod
@@ -101,17 +107,9 @@ def _check_for_duplicate_project_names(
     for package in final_deps:
         project_name = package.get_project_name(config, renderer)
         if project_name in seen:
-            raise_dependency_error(
+            raise DuplicateProjectDependencyError(project_name)
-                f'Found duplicate project "{project_name}". This occurs when '
-                "a dependency has the same project name as some other "
-                "dependency."
-            )
         elif project_name == config.project_name:
-            raise_dependency_error(
+            raise DuplicateDependencyToRootError(project_name)
-                "Found a dependency with the same name as the root project "
-                f'"{project_name}". Package names must be unique in a project.'
-                " Please rename one of these packages."
-            )
         seen.add(project_name)
 
 

core/dbt/deps/tarball.py

@@ -0,0 +1,74 @@
+from dbt.contracts.project import RegistryPackageMetadata, TarballPackage
+from dbt.deps.base import PinnedPackage, UnpinnedPackage
+
+
+class TarballPackageMixin:
+    def __init__(self, tarball: str) -> None:
+        super().__init__()
+        self.tarball = tarball
+
+    @property
+    def name(self):
+        return self.tarball
+
+    def source_type(self) -> str:
+        return "tarball"
+
+
+class TarballPinnedPackage(TarballPackageMixin, PinnedPackage):
+    def __init__(self, tarball: str, package: str) -> None:
+        super().__init__(tarball)
+        # setup to recycle RegistryPinnedPackage fns
+        self.package = package
+        self.version = "tarball"
+
+    @property
+    def name(self):
+        return self.package
+
+    def get_version(self):
+        return self.version
+
+    def nice_version_name(self):
+        return f"tarball (url: {self.tarball})"
+
+    def _fetch_metadata(self, project, renderer):
+        """
+        recycle RegistryPackageMetadata so that we can use the install and
+        download_and_untar from RegistryPinnedPackage next.
+        build RegistryPackageMetadata from info passed via packages.yml since no
+        'metadata' service exists in this case.
+        """
+
+        dct = {
+            "name": self.package,
+            "packages": [],  # note: required by RegistryPackageMetadata
+            "downloads": {"tarball": self.tarball},
+        }
+
+        return RegistryPackageMetadata.from_dict(dct)
+
+    def install(self, project, renderer):
+        self._install(project, renderer)
+
+
+class TarballUnpinnedPackage(TarballPackageMixin, UnpinnedPackage[TarballPinnedPackage]):
+    def __init__(
+        self,
+        tarball: str,
+        package: str,
+    ) -> None:
+        super().__init__(tarball)
+        # setup to recycle RegistryPinnedPackage fns
+        self.package = package
+        self.version = "tarball"
+
+    @classmethod
+    def from_contract(cls, contract: TarballPackage) -> "TarballUnpinnedPackage":
+        return cls(tarball=contract.tarball, package=contract.name)
+
+    def incorporate(self, other: "TarballUnpinnedPackage") -> "TarballUnpinnedPackage":
+        return TarballUnpinnedPackage(tarball=self.tarball, package=self.package)
+
+    def resolved(self) -> TarballPinnedPackage:
+        return TarballPinnedPackage(tarball=self.tarball, package=self.package)