Issue 155: log metadata prior to verification

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 - Simplify type annotations by replacing Union and Optional with pipe character ("|") for improved readability and clarity
+- Add debug logging of metadata fields
 
 ## [3.3.2] - 2024-03-25
 

src/zimscraperlib/zim/creator.py

@@ -20,14 +20,18 @@
 from __future__ import annotations
 
 import datetime
+import io
+import logging
 import pathlib
 import re
 import weakref
 from collections.abc import Callable, Iterable
 from typing import Any
 
 import libzim.writer  # pyright: ignore
+import PIL.Image
 
+from zimscraperlib import logger
 from zimscraperlib.constants import (
     DEFAULT_DEV_ZIM_METADATA,
     FRONT_ARTICLE_MIMETYPES,
@@ -62,6 +66,9 @@
 )
 
 
+TUPLE_SIZE_2D = 2
+
+
 def mimetype_for(
     path: str,
     content: bytes | str | None = None,
@@ -146,7 +153,39 @@ def config_indexing(
         self.__indexing_configured = True
         return self
 
+    def _is_illustration_metadata_name(self, name: str) -> bool:
+        """Return True if name is a valid illustration metadata name"""
+        return name.startswith("Illustration_")
+
+    def _get_illustration_metadata_details(
+        self,
+        value: bytes,
+    ) -> str | None:
+        """Return image format for debug logging of illustration metadata"""
+        try:
+            with PIL.Image.open(io.BytesIO(value)) as img:
+                if (
+                    img is not None
+                    and img.size is tuple
+                    and len(img.size) >= TUPLE_SIZE_2D
+                ):
+                    return f"{img.format} {img.size[0]}x{img.size[1]}"
+        except BaseException as e:
+            return f"Image format issue: {e}"
+        return f"Unknown image format, {len(value)} bytes"
+
+    def _log_metadata(self):
+        for name, value in sorted(self._metadata.items()):
+            if self._is_illustration_metadata_name(name) and isinstance(value, bytes):
+                illus_md = self._get_illustration_metadata_details(value)
+            else:
+                illus_md = None
+            logger.debug(f"Metadata: {name} = {(illus_md if illus_md else value)}")
+
     def start(self):
+        if logger.isEnabledFor(logging.DEBUG):
+            self._log_metadata()
+
         if not all(self._metadata.get(key) for key in MANDATORY_ZIM_METADATA_KEYS):
             raise ValueError("Mandatory metadata are not all set.")
 

tests/zim/test_zim_creator.py

@@ -4,13 +4,15 @@
 import base64
 import datetime
 import io
+import logging
 import pathlib
 import random
 import shutil
 import subprocess
 import sys
 import tempfile
 import time
+from unittest.mock import call, patch
 
 import pytest
 from libzim.writer import Compression  # pyright: ignore
@@ -540,6 +542,80 @@ def test_check_metadata(tmp_path):
         Creator(tmp_path, "").config_dev_metadata(LongDescription="T" * 5000).start()
 
 
+@pytest.mark.parametrize(
+    "tags",
+    [
+        (
+            "wikipedia;_category:wikipedia;_pictures:no;_videos:no;_details:yes;"
+            "_ftindex:yes"
+        ),
+        (
+            [
+                "wikipedia",
+                "_category:wikipedia",
+                "_pictures:no",
+                "_videos:no",
+                "_details:yes",
+                "_ftindex:yes",
+            ]
+        ),
+    ],
+)
+@patch("zimscraperlib.zim.creator.logger", autospec=True)
+def test_start_logs_metadata_log_contents(mocked_logger, png_image, tags, tmp_path):
+    mocked_logger.isEnabledFor.side_effect = lambda level: level == logging.DEBUG
+    fpath = tmp_path / "test_config.zim"
+    with open(png_image, "rb") as fh:
+        png_data = fh.read()
+    creator = Creator(fpath, "").config_metadata(
+        Name="wikipedia_fr_football",
+        Title="English Wikipedia",
+        Creator="English speaking Wikipedia contributors",
+        Publisher="Wikipedia user Foobar",
+        Date="2009-11-21",
+        Description="All articles (without images) from the english Wikipedia",
+        LongDescription="This ZIM file contains all articles (without images)"
+        " from the english Wikipedia by 2009-11-10. The topics are...",
+        Language="eng",
+        License="CC-BY",
+        Tags=tags,
+        Flavour="nopic",
+        Source="https://en.wikipedia.org/",
+        Scraper="mwoffliner 1.2.3",
+        Illustration_48x48_at_1=png_data,
+        TestMetadata="Test Metadata",
+    )
+    creator.start()
+    creator.finish()
+    mocked_logger.debug.assert_has_calls(
+        [
+            call("Metadata: Creator = English speaking Wikipedia contributors"),
+            call("Metadata: Date = 2009-11-21"),
+            call(
+                "Metadata: Description = All articles (without images) from the "
+                "english Wikipedia"
+            ),
+            call("Metadata: Flavour = nopic"),
+            call("Metadata: Illustration_48x48@1 = PNG 48x48"),
+            call("Metadata: Language = eng"),
+            call("Metadata: License = CC-BY"),
+            call(
+                "Metadata: LongDescription = This ZIM file contains all articles "
+                "(without images) from the english Wikipedia by 2009-11-10. "
+                "The topics are..."
+            ),
+            call("Metadata: Name = wikipedia_fr_football"),
+            call("Metadata: Publisher = Wikipedia user Foobar"),
+            call("Metadata: Relation = None"),
+            call("Metadata: Scraper = mwoffliner 1.2.3"),
+            call("Metadata: Source = https://en.wikipedia.org/"),
+            call(f"Metadata: Tags = {tags}"),
+            call("Metadata: TestMetadata = Test Metadata"),
+            call("Metadata: Title = English Wikipedia"),
+        ]
+    )
+
+
 def test_relax_metadata(tmp_path):
     Creator(tmp_path, "", disable_metadata_checks=True).config_dev_metadata(
         Description="T" * 90