any-file to PDF (Phase 1): converters/ dispatcher, images/text/md/csv/json/xml/svg/pdf-passthrough, 112 tests green

converters/text_converter.py

@@ -0,0 +1,55 @@
+"""Plain text (.txt) and log (.log) -> PDF.
+
+Decode ladder (no mojibake on legacy files, never raises):
+  1. strict UTF-8            -> valid UTF-8 is never second-guessed
+  2. strict windows-1252     -> its 5 undefined byte holes (0x81/8D/8F/90/9D)
+                                 make a successful strict decode a reliable
+                                 cp1252 signal (covers latin-1-ish content too)
+  3. charset-normalizer      -> best guess for other legacy encodings
+  4. UTF-8 errors=replace    -> last resort, total losslessness guarantee
+
+Empty / whitespace-only input is a job error ("empty file: ..."). The text
+is wrapped in <pre> with PRE_CSS (monospace, wrapped, A4) so line structure
+and indentation survive the render.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+
+from . import common
+
+
+def decode_bytes(raw: bytes) -> str:
+    """Best-effort decode ladder; see module docstring."""
+    try:
+        return raw.decode("utf-8")
+    except UnicodeDecodeError:
+        pass
+    try:
+        return raw.decode("cp1252")
+    except UnicodeDecodeError:
+        pass
+    from charset_normalizer import from_bytes
+
+    best = from_bytes(raw).best()
+    if best is not None:
+        return str(best)
+    return raw.decode("utf-8", errors="replace")
+
+
+def convert(path: Path, job_id: str, progress_cb=None, output_dir=None,
+            source_name=None) -> str:
+    """Render a plain-text or log file to a monospace PDF."""
+    raw = path.read_bytes()
+    if not raw.strip():
+        raise ValueError("empty file: nothing to convert")
+    text = decode_bytes(raw)
+
+    def _build():
+        return f"<html><body><pre>{common.escape(text)}</pre></body></html>", path.name
+
+    return common.convert_single(
+        path, job_id, build_html=_build, css=common.PRE_CSS,
+        progress_cb=progress_cb, output_dir=output_dir,
+        name_src=source_name or path.name,
+    )