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 }}

tests/test_verify_pdf.py

@@ -0,0 +1,85 @@
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from tools.verify_pdf import VerificationError, parse_page_count, run_tool, verify_pdf
+
+
+class ParsePageCountTests(unittest.TestCase):
+    def test_parses_pdfinfo_page_count(self):
+        self.assertEqual(parse_page_count("Title: Example\nPages:          2\n"), 2)
+
+    def test_rejects_output_without_page_count(self):
+        with self.assertRaisesRegex(VerificationError, "did not contain a page count"):
+            parse_page_count("Title: Example\n")
+
+
+class VerifyPdfTests(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.pdf = Path(self.temp_dir.name) / "example.pdf"
+        self.pdf.touch()
+
+    def tearDown(self):
+        self.temp_dir.cleanup()
+
+    @patch("tools.verify_pdf.run_tool")
+    def test_accepts_expected_pages_and_text(self, mock_run_tool):
+        mock_run_tool.side_effect = [
+            "Pages:          2\n",
+            "Professional\nExperience   [your.email@example.com]\n",
+        ]
+
+        verify_pdf(
+            self.pdf,
+            expected_pages=2,
+            min_chars=20,
+            required_text=("Professional Experience", "[your.email@example.com]"),
+        )
+
+    @patch("tools.verify_pdf.run_tool")
+    def test_rejects_wrong_page_count(self, mock_run_tool):
+        mock_run_tool.return_value = "Pages:          3\n"
+
+        with self.assertRaisesRegex(VerificationError, "expected 2 page.*found 3"):
+            verify_pdf(self.pdf, expected_pages=2)
+
+    @patch("tools.verify_pdf.run_tool")
+    def test_rejects_too_little_extractable_text(self, mock_run_tool):
+        mock_run_tool.return_value = "short"
+
+        with self.assertRaisesRegex(VerificationError, "expected at least 20"):
+            verify_pdf(self.pdf, min_chars=20)
+
+    @patch("tools.verify_pdf.run_tool")
+    def test_rejects_missing_required_text(self, mock_run_tool):
+        mock_run_tool.return_value = "Readable text, but not the expected section."
+
+        with self.assertRaisesRegex(VerificationError, "Professional Experience"):
+            verify_pdf(self.pdf, required_text=("Professional Experience",))
+
+    def test_rejects_missing_pdf(self):
+        with self.assertRaisesRegex(VerificationError, "PDF does not exist"):
+            verify_pdf(Path(self.temp_dir.name) / "missing.pdf")
+
+
+class RunToolTests(unittest.TestCase):
+    @patch("tools.verify_pdf.subprocess.run", side_effect=FileNotFoundError)
+    def test_reports_missing_poppler_command(self, _mock_run):
+        with self.assertRaisesRegex(VerificationError, "install poppler-utils"):
+            run_tool(["pdftotext", "example.pdf", "-"])
+
+    @patch("tools.verify_pdf.subprocess.run")
+    def test_reports_unreadable_pdf(self, mock_run):
+        mock_run.side_effect = subprocess.CalledProcessError(
+            1, ["pdfinfo", "example.pdf"], stderr="invalid PDF"
+        )
+
+        with self.assertRaisesRegex(VerificationError, "invalid PDF"):
+            run_tool(["pdfinfo", "example.pdf"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tools/verify_pdf.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+"""Verify that a generated PDF has the expected pages and extractable text."""
+
+import argparse
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+
+class VerificationError(Exception):
+    """Raised when a generated PDF does not satisfy its checks."""
+
+
+def run_tool(command):
+    try:
+        return subprocess.run(
+            command,
+            check=True,
+            capture_output=True,
+            text=True,
+        ).stdout
+    except FileNotFoundError as exc:
+        raise VerificationError(
+            f"required command '{command[0]}' was not found; install poppler-utils"
+        ) from exc
+    except subprocess.CalledProcessError as exc:
+        detail = (exc.stderr or "").strip() or (exc.stdout or "").strip()
+        detail = detail or "command failed"
+        raise VerificationError(f"{command[0]} could not read the PDF: {detail}") from exc
+
+
+def parse_page_count(pdfinfo_output):
+    match = re.search(r"^Pages:\s+(\d+)\s*$", pdfinfo_output, re.MULTILINE)
+    if not match:
+        raise VerificationError("pdfinfo output did not contain a page count")
+    return int(match.group(1))
+
+
+def normalize_text(text):
+    return " ".join(text.split())
+
+
+def verify_pdf(pdf_path, expected_pages=None, min_chars=1, required_text=()):
+    pdf_path = Path(pdf_path)
+    if not pdf_path.is_file():
+        raise VerificationError(f"PDF does not exist: {pdf_path}")
+
+    if expected_pages is not None:
+        actual_pages = parse_page_count(run_tool(["pdfinfo", str(pdf_path)]))
+        if actual_pages != expected_pages:
+            raise VerificationError(
+                f"expected {expected_pages} page(s), found {actual_pages}"
+            )
+
+    extracted_text = normalize_text(
+        run_tool(["pdftotext", "-layout", str(pdf_path), "-"])
+    )
+    if len(extracted_text) < min_chars:
+        raise VerificationError(
+            f"text layer has {len(extracted_text)} character(s); expected at least {min_chars}"
+        )
+
+    for required in required_text:
+        if normalize_text(required) not in extracted_text:
+            raise VerificationError(f"text layer is missing required text: {required!r}")
+
+
+def build_parser():
+    parser = argparse.ArgumentParser(
+        description="Verify a PDF's page count and ATS-readable text layer."
+    )
+    parser.add_argument("pdf", type=Path, help="PDF file to verify")
+    parser.add_argument("--pages", type=int, help="required exact page count")
+    parser.add_argument(
+        "--min-chars",
+        type=int,
+        default=1,
+        help="minimum non-whitespace text-layer characters (default: 1)",
+    )
+    parser.add_argument(
+        "--contains",
+        action="append",
+        default=[],
+        help="text that must appear after whitespace normalization; repeatable",
+    )
+    return parser
+
+
+def main(argv=None):
+    args = build_parser().parse_args(argv)
+    try:
+        verify_pdf(args.pdf, args.pages, args.min_chars, args.contains)
+    except VerificationError as exc:
+        print(f"Error: {args.pdf}: {exc}", file=sys.stderr)
+        return 1
+    print(f"Verified {args.pdf}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())