BabelDOC 0.4.3__tar.gz → 0.4.5__tar.gz

{babeldoc-0.4.3 → babeldoc-0.4.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.4.3
+Version: 0.4.5
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues

babeldoc-0.4.5/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.4.5"

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.4.3"
+__version__ = "0.4.5"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/format/pdf/document_il/backend/pdf_creater.py

@@ -331,7 +331,7 @@ class PDFCreater:
         self,
         draw_op: BitStream,
         rectangle: il_version_1.PdfRectangle,
-        line_width: float = 0.5,
+        line_width: float = 0.4,
     ):
         """Draw a rectangle in PDF for visualization purposes.
 

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/format/pdf/document_il/midend/add_debug_information.py

@@ -3,7 +3,6 @@ import logging
 import babeldoc.format.pdf.document_il.il_version_1 as il_version_1
 from babeldoc.format.pdf.document_il import GraphicState
 from babeldoc.format.pdf.document_il.utils.style_helper import BLUE
-from babeldoc.format.pdf.document_il.utils.style_helper import CYAN
 from babeldoc.format.pdf.document_il.utils.style_helper import ORANGE
 from babeldoc.format.pdf.document_il.utils.style_helper import TEAL
 from babeldoc.format.pdf.document_il.utils.style_helper import YELLOW
@@ -133,9 +132,9 @@ class AddDebugInformation:
                                 char.visual_bbox.box, TEAL, line_width=0.2
                             ),
                         )
-                        page.pdf_rectangle.append(
-                            self._create_rectangle(char.box, CYAN, line_width=0.2),
-                        )
+                        # page.pdf_rectangle.append(
+                        #     self._create_rectangle(char.box, CYAN, line_width=0.2),
+                        # )
 
             for xobj in page.pdf_xobject:
                 new_paragraphs.append(

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/format/pdf/high_level.py

@@ -491,7 +491,7 @@ def do_translate(
                         pm.total_parts = len(split_points)
 
                         # Process parts serially
-                        results: dict[int, TranslateResult] = {}
+                        results: dict[int, TranslateResult | None] = {}
                         original_watermark_mode = (
                             translation_config.watermark_output_mode
                         )
@@ -515,6 +515,12 @@ def do_translate(
                                 part_config.page_ranges = [
                                     (x, x) for x in should_translate_pages
                                 ]
+                                if (
+                                    translation_config.only_include_translated_page
+                                    and not should_translate_pages
+                                ):
+                                    results[i] = None
+                                    continue
 
                                 # Only first part should do scanned detection if enabled
                                 if i > 0:
@@ -805,6 +811,9 @@ def _do_translate_single(
     docs = il_creater.create_il()
     logger.debug(f"finish create il from {temp_pdf_path}")
     del il_creater
+    if translation_config.only_include_translated_page and not docs.page:
+        return None
+
     if translation_config.debug:
         xml_converter.write_json(
             docs,

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/format/pdf/result_merger.py

@@ -16,7 +16,9 @@ class ResultMerger:
     def __init__(self, translation_config: TranslationConfig):
         self.config = translation_config
 
-    def merge_results(self, results: dict[int, TranslateResult]) -> TranslateResult:
+    def merge_results(
+        self, results: dict[int, TranslateResult | None]
+    ) -> TranslateResult:
         """Merge multiple translation results into one"""
         if not results:
             raise ValueError("No results to merge")
@@ -35,7 +37,7 @@ class ResultMerger:
         dual_file_name_no_watermark = (
             f"{basename}{debug_suffix}.{self.config.lang_out}.dual.pdf"
         )
-
+        results = {k: v for k, v in results.items() if v is not None}
         # Sort results by part index
         sorted_results = dict(sorted(results.items()))
         first_result = next(iter(sorted_results.values()))

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/format/pdf/translation_config.py

@@ -354,7 +354,7 @@ class TranslationConfig:
         if part_index in self._part_working_dirs:
             part_dir = self._part_working_dirs[part_index]
             if part_dir.exists():
-                shutil.rmtree(part_dir)
+                shutil.rmtree(part_dir, ignore_errors=True)
             del self._part_working_dirs[part_index]
 
     def cleanup_temp_files(self):
@@ -364,7 +364,7 @@ class TranslationConfig:
                 self.cleanup_part_working_dir(part_index)
             if self._is_temp_dir:
                 logger.info(f"cleanup temp files: {self.working_dir}")
-                shutil.rmtree(self.working_dir)
+                shutil.rmtree(self.working_dir, ignore_errors=True)
         except Exception:
             logger.exception("Error cleaning up temporary files")
 

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.4.3"
+__version__ = "0.4.5"
 
 
 def create_parser():

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/pdfminer/pdffont.py

@@ -8,6 +8,7 @@ from typing import TYPE_CHECKING
 from typing import Any
 from typing import BinaryIO
 from typing import cast
+import freetype
 
 from babeldoc.pdfminer.casting import safe_float
 from babeldoc.pdfminer.casting import safe_rect_list
@@ -749,99 +750,16 @@ class TrueTypeFont:
     def create_unicode_map(self) -> FileUnicodeMap:
         if b"cmap" not in self.tables:
             raise TrueTypeFont.CMapNotFound
-        (base_offset, length) = self.tables[b"cmap"]
         fp = self.fp
-        fp.seek(base_offset)
-        (version, nsubtables) = cast(tuple[int, int], struct.unpack(">HH", fp.read(4)))
-        subtables: list[tuple[int, int, int]] = []
-        for i in range(nsubtables):
-            subtables.append(
-                cast(tuple[int, int, int], struct.unpack(">HHL", fp.read(8))),
-            )
-        char2gid: dict[int, int] = {}
-        # Only supports subtable type 0, 2 and 4.
-        for platform_id, encoding_id, st_offset in subtables:
-            # Skip non-Unicode cmaps.
-            # https://docs.microsoft.com/en-us/typography/opentype/spec/cmap
-            if not (platform_id == 0 or (platform_id == 3 and encoding_id in [1, 10])):
-                continue
-            fp.seek(base_offset + st_offset)
-            (fmttype, fmtlen, fmtlang) = cast(
-                tuple[int, int, int],
-                struct.unpack(">HHH", fp.read(6)),
-            )
-            if fmttype == 0:
-                char2gid.update(
-                    enumerate(
-                        cast(tuple[int, ...], struct.unpack(">256B", fp.read(256))),
-                    ),
-                )
-            elif fmttype == 2:
-                subheaderkeys = cast(
-                    tuple[int, ...],
-                    struct.unpack(">256H", fp.read(512)),
-                )
-                firstbytes = [0] * 8192
-                for i, k in enumerate(subheaderkeys):
-                    firstbytes[k // 8] = i
-                nhdrs = max(subheaderkeys) // 8 + 1
-                hdrs: list[tuple[int, int, int, int, int]] = []
-                for i in range(nhdrs):
-                    (firstcode, entcount, delta, offset) = cast(
-                        tuple[int, int, int, int],
-                        struct.unpack(">HHhH", fp.read(8)),
-                    )
-                    hdrs.append((i, firstcode, entcount, delta, fp.tell() - 2 + offset))
-                for i, firstcode, entcount, delta, pos in hdrs:
-                    if not entcount:
-                        continue
-                    first = firstcode + (firstbytes[i] << 8)
-                    fp.seek(pos)
-                    for c in range(entcount):
-                        gid = cast(tuple[int], struct.unpack(">H", fp.read(2)))[0]
-                        if gid:
-                            gid += delta
-                        char2gid[first + c] = gid
-            elif fmttype == 4:
-                (segcount, _1, _2, _3) = cast(
-                    tuple[int, int, int, int],
-                    struct.unpack(">HHHH", fp.read(8)),
-                )
-                segcount //= 2
-                ecs = cast(
-                    tuple[int, ...],
-                    struct.unpack(">%dH" % segcount, fp.read(2 * segcount)),
-                )
-                fp.read(2)
-                scs = cast(
-                    tuple[int, ...],
-                    struct.unpack(">%dH" % segcount, fp.read(2 * segcount)),
-                )
-                idds = cast(
-                    tuple[int, ...],
-                    struct.unpack(">%dh" % segcount, fp.read(2 * segcount)),
-                )
-                pos = fp.tell()
-                idrs = cast(
-                    tuple[int, ...],
-                    struct.unpack(">%dH" % segcount, fp.read(2 * segcount)),
-                )
-                for ec, sc, idd, idr in zip(ecs, scs, idds, idrs, strict=False):
-                    if idr:
-                        fp.seek(pos + idr)
-                        for c in range(sc, ec + 1):
-                            b = cast(tuple[int], struct.unpack(">H", fp.read(2)))[0]
-                            char2gid[c] = (b + idd) & 0xFFFF
-                    else:
-                        for c in range(sc, ec + 1):
-                            char2gid[c] = (c + idd) & 0xFFFF
-            else:
-                assert False, str(("Unhandled", fmttype))
-        if not char2gid:
+        char2gid = []
+        try:
+            face = freetype.Face(fp)
+            char2gid = list(face.get_chars())
+        except Exception:
             raise TrueTypeFont.CMapNotFound
         # create unicode map
         unicode_map = FileUnicodeMap()
-        for char, gid in char2gid.items():
+        for char, gid in char2gid:
             unicode_map.add_cid2unichr(gid, char)
         return unicode_map
 

{babeldoc-0.4.3 → babeldoc-0.4.5}/babeldoc/tools/italic_assistance.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 import orjson
 from babeldoc.const import CACHE_FOLDER
-from babeldoc.format.pdf.document_il.midend.styles_and_formulas import StylesAndFormulas
+from babeldoc.format.pdf.document_il.utils.formular_helper import is_formulas_font
 from babeldoc.format.pdf.translation_config import TranslationConfig
 from rich.console import Console
 from rich.table import Table
@@ -252,7 +252,6 @@ def main():
     translation_config = TranslationConfig(
         *[None for _ in range(3)], lang_out="zh_cn", doc_layout_model=1
     )
-    checker = StylesAndFormulas(translation_config)
 
     # Create table
     table = Table(title="Font Recognition Results")
@@ -266,7 +265,7 @@ def main():
     for each_font in fonts:
         page_index, font_name, paragraph_index, font_debug_id = each_font
 
-        if checker.is_formulas_font(font_name):
+        if is_formulas_font(font_name, None):
             table.add_row(
                 str(page_index),
                 str(paragraph_index),

{babeldoc-0.4.3 → babeldoc-0.4.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.4.3"
+version = "0.4.5"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -157,7 +157,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.4.3"
+current_version = "0.4.5"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.4.3 → babeldoc-0.4.5}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.4.3"
+version = "0.4.5"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },
@@ -2333,6 +2333,7 @@ sdist = { url = "https://files.pythonhosted.org/packages/bd/62/d29612ca33b7844e7
 wheels = [
     { url = "https://files.pythonhosted.org/packages/32/5a/3399a2caf51c91db650de57464465b830c2d4ea15b23d24a98182202b704/pymupdf-1.26.1-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:32296f12a7c7f36febd59cee77823a54490313bcaba9879b17def6518186f94e", size = 23054640, upload-time = "2025-06-11T22:14:07.439Z" },
     { url = "https://files.pythonhosted.org/packages/64/e0/cc3ec6a4d5ada8992b8610f134565ceb517243f12736b50d795cb3459315/pymupdf-1.26.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:aad7949eca62aca40854510cdb125cf873b181726dc9497a90834200f31faa63", size = 22402766, upload-time = "2025-06-11T22:14:25.557Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/cf/d5b1cd775a17a7b83e25cbf4c46f64cf1352c962ca97646e3e01953cf0df/pymupdf-1.26.1-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3b62c4d443121ed9a2eb967c3a0e45f8dbabcc838db8604ece02c4e868808edc", size = 23448474, upload-time = "2025-06-20T17:51:56.446Z" },
     { url = "https://files.pythonhosted.org/packages/82/9f/e7101bd24a0f5cbfa0310c8e5c3a8ec0dd9a86986812ff86ac2fbd273c92/pymupdf-1.26.1-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:a65c411eb1cbb79e40c307e10fbad23658f19e9d7334ac4de21d24b58009a7b9", size = 24056183, upload-time = "2025-06-11T22:14:53.777Z" },
     { url = "https://files.pythonhosted.org/packages/99/39/23ac15cf0edc2877ef366dc7ae041ac199d212433c2c3113661d1a1d5ad0/pymupdf-1.26.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:26cebdcc1b2b7a7445423599ce2e0000f2be0333cce0fa0e6846e5a7da46f965", size = 24258802, upload-time = "2025-06-11T22:15:20.499Z" },
     { url = "https://files.pythonhosted.org/packages/e1/8c/56bd5951128d5c5c0b64d2942090c2cd7bc44302bac991b941ac736e3d63/pymupdf-1.26.1-cp39-abi3-win32.whl", hash = "sha256:82ed9e106cf564fc959c0691c374ba68443086ba1a1c9f26128eebbc3e6df9e5", size = 16927933, upload-time = "2025-06-11T22:15:59.72Z" },

babeldoc-0.4.3/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.4.3"