ci: verify PDF page counts and text layers via poppler (#145)

.github/workflows/ci.yml

@@ -3,8 +3,9 @@
 #
 # Fork-friendly by design: forks personalize CLAUDE.md, the skill files, and
 # cv/main_example.tex via /setup, so the placeholder-integrity job and the
-# exact page-count assertions run only on the upstream template repo. Compile
-# success and lint correctness are asserted everywhere.
+# exact page-count/content assertions run only on the upstream template repo.
+# Compile success, lint correctness, and an extractable PDF text layer are
+# asserted everywhere.
 #
 # Deliberately NOT here: live smoke tests of the job-portal CLIs. They hit
 # real portals (network-flaky, and the linkedin-search skill is personal-use
@@ -102,10 +103,16 @@ jobs:
     container: texlive/texlive:latest
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+      - name: Install PDF inspection tools
+        run: |
+          if ! command -v pdfinfo >/dev/null || ! command -v pdftotext >/dev/null; then
+            apt-get update
+            apt-get install -y --no-install-recommends poppler-utils
+          fi
       - name: Compile CV example (lualatex)
         run: |
           cd cv
-          lualatex -interaction=nonstopmode main_example.tex
+          lualatex -interaction=nonstopmode -halt-on-error main_example.tex
           test -f main_example.pdf
           if grep -q '^!' main_example.log; then
             echo '::error::lualatex reported errors compiling cv/main_example.tex'
@@ -115,20 +122,28 @@ jobs:
       - name: Compile cover letter example (xelatex)
         run: |
           cd cover_letters
-          xelatex -interaction=nonstopmode cover_example.tex
+          xelatex -interaction=nonstopmode -halt-on-error cover_example.tex
           test -f cover_example.pdf
           if grep -q '^!' cover_example.log; then
             echo '::error::xelatex reported errors compiling cover_letters/cover_example.tex'
             grep -A3 '^!' cover_example.log
             exit 1
           fi
-      - name: Assert exact page counts (upstream template only)
+      - name: Verify extractable PDF text
+        run: |
+          python3 tools/verify_pdf.py cv/main_example.pdf --min-chars 100
+          python3 tools/verify_pdf.py cover_letters/cover_example.pdf --min-chars 100
+      - name: Assert stock PDF structure (upstream template only)
         if: github.repository == 'MadsLorentzen/ai-job-search'
         run: |
-          grep -q 'Output written on main_example.pdf (2 pages' cv/main_example.log \
-            || { echo '::error::cv/main_example.tex no longer compiles to exactly 2 pages'; exit 1; }
-          grep -q 'Output written on cover_example.pdf (1 page' cover_letters/cover_example.log \
-            || { echo '::error::cover_letters/cover_example.tex no longer compiles to exactly 1 page'; exit 1; }
+          python3 tools/verify_pdf.py cv/main_example.pdf \
+            --pages 2 \
+            --contains '[your.email@example.com]' \
+            --contains 'Professional Experience'
+          python3 tools/verify_pdf.py cover_letters/cover_example.pdf \
+            --pages 1 \
+            --contains 'your.email@example.com' \
+            --contains 'Dear [Hiring Manager / Team]'
 
   cli-checks:
     name: CLI checks ${{ matrix.tool }}