BabelDOC 0.5.10__tar.gz → 0.5.11__tar.gz

{babeldoc-0.5.10 → babeldoc-0.5.11}/.gitignore

@@ -45,4 +45,5 @@ uv.lock
 CLAUDE.md
 /.claude
 babeldoc/format/playground
-temp.jpg
+temp.jpg
+AGENTS.md

{babeldoc-0.5.10 → babeldoc-0.5.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.10
+Version: 0.5.11
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -81,6 +81,7 @@ Description-Content-Type: text/markdown
     <img src="https://img.shields.io/github/license/funstory-ai/BabelDOC"></a>
   <a href="https://t.me/+Z9_SgnxmsmA5NzBl">
     <img src="https://img.shields.io/badge/Telegram-2CA5E0?style=flat-squeare&logo=telegram&logoColor=white"></a>
+  <a href="https://deepwiki.com/funstory-ai/BabelDOC"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 </p>
 
 <a href="https://trendshift.io/repositories/13358" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13358" alt="funstory-ai%2FBabelDOC | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

{babeldoc-0.5.10 → babeldoc-0.5.11}/README.md

@@ -25,6 +25,7 @@
     <img src="https://img.shields.io/github/license/funstory-ai/BabelDOC"></a>
   <a href="https://t.me/+Z9_SgnxmsmA5NzBl">
     <img src="https://img.shields.io/badge/Telegram-2CA5E0?style=flat-squeare&logo=telegram&logoColor=white"></a>
+  <a href="https://deepwiki.com/funstory-ai/BabelDOC"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 </p>
 
 <a href="https://trendshift.io/repositories/13358" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13358" alt="funstory-ai%2FBabelDOC | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

babeldoc-0.5.11/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.5.11"

{babeldoc-0.5.10 → babeldoc-0.5.11}/babeldoc/babeldoc_exception/BabelDOCException.py

@@ -6,3 +6,8 @@ class ScannedPDFError(Exception):
 class ExtractTextError(Exception):
     def __init__(self, message):
         super().__init__(message)
+
+
+class InputFileGeneratedByBabelDOCError(Exception):
+    def __init__(self, message):
+        super().__init__(message)

{babeldoc-0.5.10 → babeldoc-0.5.11}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.5.10"
+__version__ = "0.5.11"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

babeldoc-0.5.11/babeldoc/format/pdf/babelpdf/cidfont.py

@@ -0,0 +1,60 @@
+import re
+from io import BytesIO
+
+import freetype
+
+
+def indirect(obj):
+    if isinstance(obj, tuple) and obj[0] == "xref":
+        return int(obj[1].split(" ")[0])
+
+
+def get_xref(doc, xref, key):
+    obj = doc.xref_get_key(xref, key)
+    if obj[0] == "xref":
+        return indirect(obj)
+
+
+def get_font_file(doc, xref):
+    if idx := get_xref(doc, xref, "FontFile"):
+        return doc.xref_stream(idx)
+    if idx := get_xref(doc, xref, "FontFile2"):
+        return doc.xref_stream(idx)
+    if idx := get_xref(doc, xref, "FontFile3"):
+        return doc.xref_stream(idx)
+
+
+def get_font_descriptor(doc, xref):
+    if idx := get_xref(doc, xref, "FontDescriptor"):
+        return get_font_file(doc, idx)
+
+
+def get_descendant_fonts(doc, xref):
+    obj = doc.xref_get_key(xref, "DescendantFonts")
+    array_text = ""
+    if obj[0] == "xref":
+        array_text = doc.xref_object(indirect(obj))
+    elif obj[0] == "array":
+        array_text = obj[1]
+    if m := re.search(r"\d+", array_text):
+        return get_font_descriptor(doc, int(m.group(0)))
+
+
+def get_glyph_bbox(face, g):
+    face.load_glyph(g, freetype.FT_LOAD_NO_SCALE)
+    cbox = face.glyph.outline.get_bbox()
+    return cbox.xMin, cbox.yMin, cbox.xMax, cbox.yMax
+
+
+def get_face_bbox(blob):
+    face = freetype.Face(BytesIO(blob))
+    scale = 1000 / face.units_per_EM
+    bbox_list = [get_glyph_bbox(face, code) for code in range(face.num_glyphs)]
+    bbox_list = [[v * scale for v in bbox] for bbox in bbox_list]
+    return bbox_list
+
+
+def get_cidfont_bbox(doc, xref):
+    if doc.xref_get_key(xref, "Subtype")[1] == "/Type0":
+        if blob := get_descendant_fonts(doc, xref):
+            return get_face_bbox(blob)