ci: merge main to release

.github/workflows/build-base-app.yml

@@ -14,11 +14,18 @@ jobs:
   publish:
     runs-on: ubuntu-latest
     permissions:
-      contents: read
+      contents: write
       packages: write
 
     steps:
     - uses: actions/checkout@v4
+      with:
+        token: ${{ secrets.GH_COMMON_TOKEN }}
+
+    - name: Set Version
+      run: |
+        printf -v CURDATE '%(%Y%m%dT%H%M)T' -1
+        echo "IMGVERSION=$CURDATE" >> $GITHUB_ENV
 
     - name: Set up QEMU
       uses: docker/setup-qemu-action@v3
@@ -42,4 +49,18 @@ jobs:
         file: docker/base.Dockerfile
         platforms: linux/amd64,linux/arm64
         push: true
-        tags: ghcr.io/ietf-tools/datatracker-app-base:latest
+        tags: |
+          ghcr.io/ietf-tools/datatracker-app-base:${{ env.IMGVERSION }}
+          ghcr.io/ietf-tools/datatracker-app-base:latest
+
+    - name: Update version references
+      run: |
+        sed -i "1s/.*/FROM ghcr.io\/ietf-tools\/datatracker-app-base:${{ env.IMGVERSION }}/" dev/build/Dockerfile
+        echo "${{ env.IMGVERSION }}" > dev/build/TARGET_BASE
+
+    - name: Commit CHANGELOG.md
+      uses: stefanzweifel/git-auto-commit-action@v5
+      with:
+        branch: main
+        commit_message: 'ci: update base image target version to ${{ env.IMGVERSION }}'
+        file_pattern: dev/build/Dockerfile dev/build/TARGET_BASE

.github/workflows/build.yml

@@ -63,6 +63,7 @@ jobs:
       pkg_version: ${{ steps.buildvars.outputs.pkg_version }}
       from_tag: ${{ steps.semver.outputs.nextStrict }}
       to_tag: ${{ steps.semver.outputs.current }}
+      base_image_version: ${{ steps.baseimgversion.outputs.base_image_version }}
 
     steps:   
     - uses: actions/checkout@v4
@@ -122,6 +123,11 @@ jobs:
           echo "::notice::Non-production build ${{ steps.semverdev.outputs.nextMajorStrict }}.0.0-dev.$GITHUB_RUN_NUMBER created using branch $GITHUB_REF_NAME"
         fi
 
+    - name: Get Base Image Target Version
+      id: baseimgversion
+      run: |
+        echo "base_image_version=$(sed -n '1p' dev/build/TARGET_BASE)" >> $GITHUB_OUTPUT
+
   # -----------------------------------------------------------------
   # TESTS
   # -----------------------------------------------------------------
@@ -133,6 +139,7 @@ jobs:
     needs: [prepare]
     with:
       ignoreLowerCoverage: ${{ github.event.inputs.ignoreLowerCoverage == 'true' }}
+      targetBaseVersion: ${{ needs.prepare.outputs.base_image_version }}
 
   # -----------------------------------------------------------------
   # RELEASE
@@ -200,6 +207,7 @@ jobs:
         SKIP_TESTS: ${{ github.event.inputs.skiptests }}
         DEBIAN_FRONTEND: noninteractive
         BROWSERSLIST_IGNORE_OLD_DATA: 1
+        TARGETBASE: ${{ needs.prepare.outputs.base_image_version }}
       with:
         host: ${{ steps.azlaunch.outputs.ipaddr }}
         port: 22
@@ -310,7 +318,7 @@ jobs:
           echo "=========================================================================="
           echo "Collecting statics..."
           echo "=========================================================================="
-          sudo docker run --rm --name collectstatics -v $(pwd):/workspace ghcr.io/ietf-tools/datatracker-app-base:latest sh dev/build/collectstatics.sh
+          sudo docker run --rm --name collectstatics -v $(pwd):/workspace ghcr.io/ietf-tools/datatracker-app-base:$TARGETBASE sh dev/build/collectstatics.sh
           echo "Pushing statics..."
           cd static
           aws s3 sync . s3://static/dt/$PKG_VERSION --only-show-errors

.github/workflows/tests.yml

@@ -8,12 +8,17 @@ on:
         default: false
         required: true
         type: boolean
+      targetBaseVersion:
+        description: 'Target Base Image Version'
+        default: latest
+        required: true
+        type: string
 
 jobs:
   tests-python:
     name: Python Tests
     runs-on: ubuntu-latest
-    container: ghcr.io/ietf-tools/datatracker-app-base:latest
+    container: ghcr.io/ietf-tools/datatracker-app-base:${{ inputs.targetBaseVersion }}
 
     services:
       db:
@@ -43,7 +48,7 @@ jobs:
           exit 1
         fi
         echo "Running tests..."
-        if [[ "x${{ github.event.inputs.ignoreLowerCoverage }}" == "xtrue" ]]; then
+        if [[ "x${{ inputs.ignoreLowerCoverage }}" == "xtrue" ]]; then
           echo "Lower coverage failures will be ignored."
           HOME=/root ./ietf/manage.py test -v2 --validate-html-harder --settings=settings_test --ignore-lower-coverage
         else
@@ -114,7 +119,7 @@ jobs:
   tests-playwright-legacy:
     name: Playwright Legacy Tests
     runs-on: ubuntu-latest
-    container: ghcr.io/ietf-tools/datatracker-app-base:latest
+    container: ghcr.io/ietf-tools/datatracker-app-base:${{ inputs.targetBaseVersion }}
     strategy:
       fail-fast: false
       matrix:

dev/build/Dockerfile

@@ -1,4 +1,4 @@
-FROM ghcr.io/ietf-tools/datatracker-app-base:2024102800
+FROM ghcr.io/ietf-tools/datatracker-app-base:20241029T1632
 LABEL maintainer="IETF Tools Team <tools-discuss@ietf.org>"
 
 ENV DEBIAN_FRONTEND=noninteractive

dev/build/TARGET_BASE

@@ -0,0 +1 @@
+20241029T1632

ietf/doc/models.py

@@ -530,22 +530,29 @@ def replaces(self):
     def replaced_by(self):
         return set([ r.document for r in self.related_that("replaces") ])
 
-    def text(self):
+    def text(self, size = -1):
         path = self.get_file_name()
         root, ext =  os.path.splitext(path)
         txtpath = root+'.txt'
         if ext != '.txt' and os.path.exists(txtpath):
             path = txtpath
         try:
             with io.open(path, 'rb') as file:
-                raw = file.read()
+                raw = file.read(size)
         except IOError:
             return None
+        text = None
         try:
             text = raw.decode('utf-8')
         except UnicodeDecodeError:
-            text = raw.decode('latin-1')
-        #
+            for back in range(1,4):
+                try:
+                    text = raw[:-back].decode('utf-8')
+                    break
+                except UnicodeDecodeError:
+                    pass
+            if text is None:
+                text = raw.decode('latin-1')
         return text
 
     def text_or_error(self):

ietf/doc/views_doc.py

@@ -84,7 +84,7 @@
 from ietf.review.utils import can_request_review_of_doc, review_assignments_to_list_for_docs, review_requests_to_list_for_docs
 from ietf.review.utils import no_review_from_teams_on_doc
 from ietf.utils import markup_txt, log, markdown
-from ietf.utils.draft import PlaintextDraft
+from ietf.utils.draft import get_status_from_draft_text
 from ietf.utils.meetecho import MeetechoAPIError, SlidesManager
 from ietf.utils.response import permission_denied
 from ietf.utils.text import maybe_split
@@ -2261,12 +2261,11 @@ def idnits2_state(request, name, rev=None):
     elif doc.intended_std_level:
         doc.deststatus = doc.intended_std_level.name
     else:
-        text = doc.text()
+         # 10000 is a conservative prefix on number of utf-8 encoded bytes to 
+         # cover at least the first 10 lines of characters
+        text = doc.text(size=10000)
         if text:
-            parsed_draft = PlaintextDraft(
-                text=doc.text(), source=name, name_from_source=False
-            )
-            doc.deststatus = parsed_draft.get_status()
+            doc.deststatus = get_status_from_draft_text(text)
         else:
             doc.deststatus = "Unknown"
     return render(

ietf/utils/draft.py

@@ -131,6 +131,24 @@ def acronym_match(s, l):
     #_debug(" s:%s; l:%s => %s; %s" % (s, l, acronym, s==acronym)) 
     return s == acronym
 
+def get_status_from_draft_text(text):
+
+    # Take prefix to shortcut work over very large drafts
+    # 5000 is conservatively much more than a full page of characters and we
+    # only want the first 10 lines.
+    text = text.strip()[:5000] # Take prefix to shortcut work over very large drafts 
+    text = re.sub(".\x08", "", text)    # Get rid of inkribbon backspace-emphasis
+    text = text.replace("\r\n", "\n")   # Convert DOS to unix
+    text = text.replace("\r", "\n")     # Convert MAC to unix
+    lines = text.split("\n")[:10]
+    status = None
+    for line in lines:
+        status_match = re.search(r"^\s*Intended [Ss]tatus:\s*(.*?)   ", line)
+        if status_match:
+            status = status_match.group(1)
+            break
+    return status
+
 class Draft:
     """Base class for drafts