easyrip 4.3.3__py3-none-any.whl → 4.5.0__py3-none-any.whl

easyrip/ripper/sub_and_font/__init__.py

@@ -0,0 +1,10 @@
+from .ass import Ass
+from .font import Font
+from .subset import load_fonts, subset
+
+__all__ = [
+    "Ass",
+    "Font",
+    "load_fonts",
+    "subset",
+]

easyrip/ripper/{font_subset → sub_and_font}/font.py

@@ -40,7 +40,13 @@ class Font:
         self.font.close()
 
 
-def load_fonts(path: str | Path, lazy: bool = True) -> list[Font]:
+def load_fonts(
+    path: str | Path,
+    *,
+    lazy: bool = True,
+    strict: bool = False,
+) -> list[Font]:
+    """strict: Skip UnicodeDecodeError font file"""
     if isinstance(path, str):
         path = Path(path)
 
@@ -59,7 +65,8 @@ def load_fonts(path: str | Path, lazy: bool = True) -> list[Font]:
                 if suffix == ".ttc"
                 else [TTFont(file=file, lazy=lazy)]
             ):
-                table_name: table__n_a_m_e | None = font.get("name")  # pyright: ignore[reportAssignmentType]
+                skip_this_font: bool = False
+                table_name: table__n_a_m_e | None = font.get("name")
 
                 if table_name is None:
                     log.warning(f"No 'name' table found in font {file}")
@@ -76,7 +83,16 @@ def load_fonts(path: str | Path, lazy: bool = True) -> list[Font]:
                     if name_id not in {1, 2}:
                         continue
 
-                    name_str: str = record.toUnicode()
+                    try:
+                        name_str: str = record.toUnicode()
+                    except UnicodeDecodeError as e:
+                        error_text = f"Unicode decode error in font \"{file}\": {e}: '{record.toUnicode('replace')}'. Skip this {'font' if strict else 'name record'}."
+                        if strict:
+                            log.error(error_text, is_format=False)
+                            skip_this_font = True
+                            break
+                        log.warning(error_text, is_format=False)
+                        continue
 
                     match name_id:
                         case 1:  # Font Family Name
@@ -94,6 +110,9 @@ def load_fonts(path: str | Path, lazy: bool = True) -> list[Font]:
                                     case "italic" | "oblique":
                                         is_italic = True
 
+                if skip_this_font:
+                    continue
+
                 if not res_font.familys:
                     log.warning(f"Font {file} has no family names. Skip this font")
                     continue
@@ -121,16 +140,18 @@ def load_fonts(path: str | Path, lazy: bool = True) -> list[Font]:
                 res_font_list.append(res_font)
 
         except TTLibError as e:
-            log.warning(f'Error loading font file "{file}": {e}')
-        except UnicodeDecodeError as e:
-            log.warning(f"Unicode decode error for font {file}: {e}")
+            log.error(f'Error loading font file "{file}": {e}')
         except Exception as e:
             log.error(f"Unexpected error for font {file}: {e}")
 
     return res_font_list
 
 
-def load_windows_fonts(lazy: bool = True) -> list[Font]:
+def load_windows_fonts(
+    *,
+    lazy: bool = True,
+    strict: bool = False,
+) -> list[Font]:
     paths: tuple[str, ...] = (
         os.path.join(os.environ["SYSTEMROOT"], "Fonts"),
         os.path.join(os.environ["LOCALAPPDATA"], "Microsoft/Windows/Fonts"),
@@ -138,7 +159,7 @@ def load_windows_fonts(lazy: bool = True) -> list[Font]:
 
     return list(
         itertools.chain.from_iterable(
-            load_fonts(path=path, lazy=lazy) for path in paths
+            load_fonts(path, lazy=lazy, strict=strict) for path in paths
         )
     )
 
@@ -149,7 +170,9 @@ def subset_font(font: Font, subset_str: str, affix: str) -> tuple[TTFont, bool]:
     # 检查哪些字符不存在于字体中
     try:
         cmap = subset_font.getBestCmap()
-        available_chars = {chr(key) for key in cmap.keys()}  # noqa: SIM118
+        if cmap is None:
+            raise Exception("cmap is None")
+        available_chars = set(map(chr, cmap))
     except Exception as e:
         raise Font_error("Can not read best cmap from '{}'", font.pathname) from e
     input_chars = set(subset_str)
@@ -191,8 +214,13 @@ def subset_font(font: Font, subset_str: str, affix: str) -> tuple[TTFont, bool]:
     # 修改 Name Record
     affix_ascii = affix.encode("ascii")
     affix_utf16be = affix.encode("utf-16-be")
-    table_name: table__n_a_m_e = font.font.get("name")  # pyright: ignore[reportAssignmentType]
-    subset_table_name: table__n_a_m_e = subset_font.get("name")  # pyright: ignore[reportAssignmentType]
+    table_name: table__n_a_m_e | None = font.font.get("name")
+    subset_table_name: table__n_a_m_e | None = subset_font.get("name")
+
+    # 这两个都是复制的，所以不可能是 None
+    assert table_name is not None
+    assert subset_table_name is not None
+
     subset_table_name.names = list[NameRecord]()  # 重写 name table
     for record in table_name.names:
         name_id = int(record.nameID)

easyrip/ripper/{font_subset → sub_and_font}/subset.py

@@ -140,22 +140,32 @@ def subset(
                     for tag, value in re.findall(
                         r"\\\s*(fn|b(?![a-zA-Z])|i(?![a-zA-Z])|r)([^\\}]*)", text
                     ):
+                        assert isinstance(tag, str) and isinstance(value, str)
+
+                        proc_value = value.strip()
+                        if proc_value.startswith("("):
+                            proc_value = proc_value[1:]
+                            if (_index := proc_value.find(")")) != -1:
+                                proc_value = proc_value[:_index]
+                            proc_value = proc_value.strip()
+
                         match tag:
                             case "fn":
-                                tag_fn = value
+                                tag_fn = proc_value
                             case "b":
-                                tag_bold = value
+                                tag_bold = proc_value
                             case "i":
-                                tag_italic = value
+                                tag_italic = proc_value
                             case "r":
-                                if value in style__font_sign:
-                                    current_font_sign = style__font_sign[value]
+                                r_value = proc_value if "(" in value else value.rstrip()
+                                if r_value in style__font_sign:
+                                    current_font_sign = style__font_sign[r_value]
                                 else:
                                     # 空为还原样式, 非样式表内样式名效果同空, 但发出不规范警告
                                     current_font_sign = default_font_sign
-                                    if value != "":
+                                    if r_value != "":
                                         log.warning(
-                                            "The \\r style '{}' not in Styles", value
+                                            "The \\r style '{}' not in Styles", r_value
                                         )
 
                     new_fontname: str = current_font_sign[0]
@@ -164,12 +174,12 @@ def subset(
                     new_bold, new_italic = current_font_sign[1].value
 
                     if tag_fn is not None:
-                        match _tag_fn := tag_fn.strip():
+                        match tag_fn:
                             case "":
                                 new_fontname = default_font_sign[0]
                             case _:
-                                _is_vertical: bool = _tag_fn[0] == "@"
-                                new_fontname = _tag_fn[1:] if _is_vertical else _tag_fn
+                                _is_vertical: bool = tag_fn.startswith("@")
+                                new_fontname = tag_fn[1:] if _is_vertical else tag_fn
 
                                 # 修改
                                 text = text.replace(
@@ -178,7 +188,7 @@ def subset(
                                 )
 
                     if tag_bold is not None:
-                        match tag_bold.strip():
+                        match tag_bold:
                             case "":
                                 new_bold = default_font_sign[1].value[0]
                             case "0":
@@ -195,7 +205,7 @@ def subset(
                                 return_res = not strict
 
                     if tag_italic is not None:
-                        match tag_italic.strip():
+                        match tag_italic:
                             case "":
                                 new_italic = default_font_sign[1].value[1]
                             case "0":
@@ -272,9 +282,9 @@ def subset(
     # 加载 Font
     fonts: Final[list[Font]] = []
     for _path in font_path_list:
-        fonts.extend(load_fonts(_path))
+        fonts.extend(load_fonts(_path, strict=strict))
     if use_win_font:
-        fonts.extend(load_windows_fonts())
+        fonts.extend(load_windows_fonts(strict=strict))
 
     font_sign__font: dict[tuple[str, Font_type], Font] = {}
     for _font in fonts:
@@ -362,6 +372,10 @@ def subset(
             f"( {key[0]} / {key[1].name} ){mapping_res}",
             deep=(strict and bool(mapping_res)),
         )
+        log.debug(
+            f"{_font.pathname}: {_font.familys} {_font.font_type.name}",
+            is_format=False,
+        )
 
     # 子集化字体
     for key, val in font__subset_str.items():

{easyrip-4.3.3.dist-info → easyrip-4.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: easyrip
-Version: 4.3.3
+Version: 4.5.0
 Author: op200
 License-Expression: AGPL-3.0-or-later
 Project-URL: Homepage, https://github.com/op200/EasyRip
@@ -21,8 +21,8 @@ Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prompt-toolkit>=3.0.52
-Requires-Dist: fonttools>=4.61.0
-Requires-Dist: pycryptodome>=3.21.0
+Requires-Dist: fonttools>=4.61.1
+Requires-Dist: pycryptodome>=3.23.0
 Dynamic: license-file
 
 # Easy Rip

{easyrip-4.3.3.dist-info → easyrip-4.5.0.dist-info}/RECORD

@@ -1,10 +1,10 @@
-easyrip/__init__.py,sha256=BlDIN9htmQXETt7M8pjYSOVrKevuuyfRn2ajQI4J7us,648
-easyrip/__main__.py,sha256=2i4xz_WNXXEiJqbs_zaVz9hvkY90dAhT_CzB38G68KA,4386
-easyrip/easyrip_command.py,sha256=xp2T-J0ahXdxDg1mnIhH7ubVicsTBkSYhhokTBQ6f5k,28659
+easyrip/__init__.py,sha256=PIvSPDgswsIkWL4dsCe87knnxKmtvcrWYzmqAwZix_M,765
+easyrip/__main__.py,sha256=ndKSOQpWOUtpVf009yqX-9vEiEjOgFDye0re45_PfQQ,4454
+easyrip/easyrip_command.py,sha256=YnwtrAh7FtN7Uk8R_Fupn96OTeWtzdCYN0p5rEFe91o,27833
 easyrip/easyrip_log.py,sha256=0V5wBwbqWt56w_NHoLmQmkTHPnPLkYZCAbhDSYnLnDw,15611
-easyrip/easyrip_main.py,sha256=gVRqRJfB8c_nCb9nJqTfbfVkmhQyDLbmywS0DPsrwRg,43460
+easyrip/easyrip_main.py,sha256=39a1cSnQUnNplX5rVTG1ECoo0_RCpQyylPu1uhArnZc,43886
 easyrip/easyrip_prompt.py,sha256=A5S7ybeJSGFkCmwdJ9TCQ_-lde7NWgkbFytZ2KnvkWI,2145
-easyrip/global_val.py,sha256=mgJ85II0MwIede9yRxY10be9kb1p8toA9LHcNzPqpzg,773
+easyrip/global_val.py,sha256=yzNIoY-_F1mkIsk39lsW7iNFbqBAB88HMg-WbE7Jg-E,773
 easyrip/utils.py,sha256=YM8gaKon-9DLt5llF-7-TE0JqDpKZrKGj7oRScLFatU,6322
 easyrip/easyrip_config/config.py,sha256=9uskiGIpYLuS-vjzNASZlhdWLWXkEVxtSjODxcZU3pc,7935
 easyrip/easyrip_config/config_key.py,sha256=wANVusz9kNqsYJUvXM7DUQn6k_G6EO2VWTHWh9dOifw,394
@@ -16,16 +16,16 @@ easyrip/easyrip_mlang/translator.py,sha256=Vg0S0p2rpMNAy3LHTdK7qKFdkPEXlOoCCXcaH
 easyrip/easyrip_web/__init__.py,sha256=tMyEeaSGeEJjND7MF0MBv9aDiDgaO3MOnppwxA70U2c,177
 easyrip/easyrip_web/http_server.py,sha256=iyulCAFQrJlz86Lrr-Dm3fhOnNCf79Bp6fVHhr0ephY,8350
 easyrip/easyrip_web/third_party_api.py,sha256=umj-QsfOa0IM60Ic2pXigVfnGfAiiC95fJSXQ-WFpJA,4419
-easyrip/ripper/__init__.py,sha256=o5gj8QRvkuVc0S9jbRjVOWXpLAaQKC0-n-o6Zx9Dowo,171
 easyrip/ripper/media_info.py,sha256=mQq_vbQ7S9fWpb39HLkoZlAL-pqNfwxewv6X776Nf50,5078
-easyrip/ripper/ripper.py,sha256=uyAZFg5PYg77q2WX_EWWDvqgIV2hta8r7UNwoqA-V_Y,62300
-easyrip/ripper/font_subset/__init__.py,sha256=a6UoRH1AU1l5FkFgQ-wQxOswLmovgVUUl3rLaJnN8Co,88
-easyrip/ripper/font_subset/ass.py,sha256=eGi1eIDWAV1Ti_BYIAcAMwrAlXJ5f_zGYte3nNu4PeE,25532
-easyrip/ripper/font_subset/font.py,sha256=-YG6zWfQeOTPJsJfCEiR-W3CR-kAuOoeVQDPVnzmuEw,7334
-easyrip/ripper/font_subset/subset.py,sha256=yj5JYZg1XPO1U0zsZUHSsOX105wrmE_g-2jLpcrvqqc,17137
-easyrip-4.3.3.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-easyrip-4.3.3.dist-info/METADATA,sha256=V3W8rWxBtl83cpLAvYhnC3UNKZIp5-O851xWATGMe3U,3506
-easyrip-4.3.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-easyrip-4.3.3.dist-info/entry_points.txt,sha256=D6GBMMTzZ-apgX76KyZ6jxMmIFqGYwU9neeLLni_qKI,49
-easyrip-4.3.3.dist-info/top_level.txt,sha256=kuEteBXm-Gf90jRQgH3-fTo-Z-Q6czSuUEqY158H4Ww,8
-easyrip-4.3.3.dist-info/RECORD,,
+easyrip/ripper/param.py,sha256=x11G7AsU-1Ol37-psKNo8AtjKDdD8YPlXeNwJSbhZxw,11082
+easyrip/ripper/ripper.py,sha256=Ru3FI7c6toMEm1qgt_5XneeIYHTTv269nS6-Dmv1f6Y,50167
+easyrip/ripper/sub_and_font/__init__.py,sha256=cBT7mxL7RRFaJXFPXuZ7RT-YK6FbnanaU5v6U9BOquw,153
+easyrip/ripper/sub_and_font/ass.py,sha256=eGi1eIDWAV1Ti_BYIAcAMwrAlXJ5f_zGYte3nNu4PeE,25532
+easyrip/ripper/sub_and_font/font.py,sha256=pzRtMrcL3ATFOMM5nsJQqSBbZtrnRodIgxLkjHai7kg,8075
+easyrip/ripper/sub_and_font/subset.py,sha256=VsFYTFuVWXW9ltkqWZIiwOIh-nGDKmW1tUv3oi5kpWw,17815
+easyrip-4.5.0.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+easyrip-4.5.0.dist-info/METADATA,sha256=10d52t-vOhqDgakGdsn0_0QLCrnMSuoMvQ9rUOwsraY,3506
+easyrip-4.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+easyrip-4.5.0.dist-info/entry_points.txt,sha256=D6GBMMTzZ-apgX76KyZ6jxMmIFqGYwU9neeLLni_qKI,49
+easyrip-4.5.0.dist-info/top_level.txt,sha256=kuEteBXm-Gf90jRQgH3-fTo-Z-Q6czSuUEqY158H4Ww,8
+easyrip-4.5.0.dist-info/RECORD,,

easyrip/ripper/__init__.py

@@ -1,10 +0,0 @@
-from .font_subset import Ass, subset
-from .media_info import Media_info
-from .ripper import Ripper
-
-__all__ = [
-    "Ass",
-    "Media_info",
-    "Ripper",
-    "subset",
-]

easyrip/ripper/font_subset/__init__.py

@@ -1,7 +0,0 @@
-from .ass import Ass
-from .subset import subset
-
-__all__ = [
-    "Ass",
-    "subset",
-]