pdfalyzer 1.17.7__tar.gz → 1.17.8__tar.gz

{pdfalyzer-1.17.7 → pdfalyzer-1.17.8}/CHANGELOG.md

@@ -1,7 +1,10 @@
 # NEXT RELEASE
 
+### 1.17.8
+* Handle `AttributeError` in `FontInfo` extraction
+
 ### 1.17.7
-* Bump `pypdf` to 6.1.3 (fixes [#31](https://github.com/michelcrypt4d4mus/pdfalyzer/issues/31), `PyMuPDF` to 1.26.5
+* Bump `pypdf` to 6.1.3 (fixes [#31](https://github.com/michelcrypt4d4mus/pdfalyzer/issues/31)), `PyMuPDF` to 1.26.5
 
 ### 1.17.6
 * Better handling for errors resulting from bugs in PyPDF

{pdfalyzer-1.17.7 → pdfalyzer-1.17.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pdfalyzer
-Version: 1.17.7
+Version: 1.17.8
 Summary: Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more.
 Home-page: https://github.com/michelcrypt4d4mus/pdfalyzer
 License: GPL-3.0-or-later

{pdfalyzer-1.17.7 → pdfalyzer-1.17.8}/pdfalyzer/pdfalyzer.py

@@ -220,14 +220,20 @@ class Pdfalyzer:
     def _extract_font_infos(self) -> None:
         """Extract information about fonts in the tree and place it in `self.font_infos`."""
         for node in self.node_iterator():
-            if isinstance(node.obj, dict) and RESOURCES in node.obj:
-                log.debug(f"Extracting fonts from node with '{RESOURCES}' key: {node}...")
-                known_font_ids = [fi.idnum for fi in self.font_infos]
+            if not (isinstance(node.obj, dict) and RESOURCES in node.obj):
+                continue
+
+            log.debug(f"Extracting fonts from node with '{RESOURCES}' key: {node}...")
+            known_font_ids = [fi.idnum for fi in self.font_infos]
 
+            try:
                 self.font_infos += [
                     fi for fi in FontInfo.extract_font_infos(node.obj)
                     if fi.idnum not in known_font_ids
                 ]
+            except AttributeError as e:
+                console.print_exception()
+                log.error(f"Failed to extract font information from node: {node}")
 
     def _build_or_find_node(self, relationship: IndirectObject, relationship_key: str) -> PdfTreeNode:
         """If node in self.nodes_encountered already then return it, otherwise build a node and store it."""

{pdfalyzer-1.17.7 → pdfalyzer-1.17.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdfalyzer"
-version = "1.17.7"
+version = "1.17.8"
 description = "Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more."
 authors = ["Michel de Cryptadamus <michel@cryptadamus.com>"]
 license = "GPL-3.0-or-later"