paddlex 3.0.2__py3-none-any.whl → 3.1.0__py3-none-any.whl

paddlex/utils/download.py

@@ -39,14 +39,14 @@ class _ProgressPrinter(object):
             str_ += "\n"
             self._last_time = 0
         if time.time() - self._last_time >= self._flush_intvl:
-            sys.stdout.write(f"\r{str_}")
+            sys.stderr.write(f"\r{str_}")
             self._last_time = time.time()
-            sys.stdout.flush()
+            sys.stderr.flush()
 
 
 def _download(url, save_path, print_progress):
     if print_progress:
-        print(f"Connecting to {url} ...")
+        print(f"Connecting to {url} ...", file=sys.stderr)
 
     with requests.get(url, stream=True, timeout=15) as r:
         r.raise_for_status()
@@ -62,7 +62,10 @@ def _download(url, save_path, print_progress):
                 total_length = int(total_length)
                 if print_progress:
                     printer = _ProgressPrinter()
-                    print(f"Downloading {os.path.basename(save_path)} ...")
+                    print(
+                        f"Downloading {os.path.basename(save_path)} ...",
+                        file=sys.stderr,
+                    )
                 for data in r.iter_content(chunk_size=4096):
                     dl += len(data)
                     f.write(data)
@@ -95,17 +98,17 @@ def _extract_tar_file(file_path, extd_dir):
                 try:
                     f.extract(file, extd_dir)
                 except KeyError:
-                    print(f"File {file} not found in the archive.")
+                    print(f"File {file} not found in the archive.", file=sys.stderr)
                 yield total_num, index
     except Exception as e:
-        print(f"An error occurred: {e}")
+        print(f"An error occurred: {e}", file=sys.stderr)
 
 
 def _extract(file_path, extd_dir, print_progress):
     """extract"""
     if print_progress:
         printer = _ProgressPrinter()
-        print(f"Extracting {os.path.basename(file_path)}")
+        print(f"Extracting {os.path.basename(file_path)}", file=sys.stderr)
 
     if zipfile.is_zipfile(file_path):
         handler = _extract_zip_file

paddlex/utils/{fonts/__init__.py → fonts.py}

@@ -17,27 +17,10 @@ from pathlib import Path
 import PIL
 from PIL import ImageFont
 
-from .. import logging
-from ..cache import CACHE_DIR
-from ..download import download
-from ..flags import LOCAL_FONT_FILE_PATH
-
-
-def get_font_file_path(file_name: str) -> str:
-    """
-    Get the path of the font file.
-
-    Returns:
-    str: The path to the font file.
-    """
-    font_path = (Path(CACHE_DIR) / "fonts" / file_name).resolve().as_posix()
-    if not Path(font_path).is_file():
-        download(
-            url=f"https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/fonts/{file_name}",
-            save_path=font_path,
-        )
-
-    return font_path
+from . import logging
+from .cache import CACHE_DIR
+from .download import download
+from .flags import LOCAL_FONT_FILE_PATH
 
 
 def create_font(txt: str, sz: tuple, font_path: str) -> ImageFont:
@@ -87,12 +70,48 @@ def create_font_vertical(
     return font
 
 
+class Font:
+    def __init__(self, font_name=None, local_path=None):
+        if local_path is None:
+            if Path(str(LOCAL_FONT_FILE_PATH)).is_file():
+                local_path = str(LOCAL_FONT_FILE_PATH)
+        self._local_path = local_path
+        if not local_path:
+            assert font_name is not None
+            self._font_name = font_name
+
+    @property
+    def path(self):
+        # HACK: download font file when needed only
+        if not self._local_path:
+            self._get_offical_font()
+        return self._local_path
+
+    def _get_offical_font(self):
+        """
+        Download the official font file.
+        """
+        font_path = (Path(CACHE_DIR) / "fonts" / self._font_name).resolve().as_posix()
+        if not Path(font_path).is_file():
+            download(
+                url=f"https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/fonts/{self._font_name}",
+                save_path=font_path,
+            )
+        self._local_path = font_path
+
+
 if Path(str(LOCAL_FONT_FILE_PATH)).is_file():
     logging.warning(
         f"Using the local font file(`{LOCAL_FONT_FILE_PATH}`) specified by `LOCAL_FONT_FILE_PATH`!"
     )
-    PINGFANG_FONT_FILE_PATH = LOCAL_FONT_FILE_PATH
-    SIMFANG_FONT_FILE_PATH = LOCAL_FONT_FILE_PATH
-else:
-    PINGFANG_FONT_FILE_PATH = get_font_file_path("PingFang-SC-Regular.ttf")
-    SIMFANG_FONT_FILE_PATH = get_font_file_path("simfang.ttf")
+
+PINGFANG_FONT = Font(font_name="PingFang-SC-Regular.ttf")
+SIMFANG_FONT = Font(font_name="simfang.ttf")
+LATIN_FONT = Font(font_name="latin.ttf")
+KOREAN_FONT = Font(font_name="korean.ttf")
+ARABIC_FONT = Font(font_name="arabic.ttf")
+CYRILLIC_FONT = Font(font_name="cyrillic.ttf")
+KANNADA_FONT = Font(font_name="kannada.ttf")
+TELUGU_FONT = Font(font_name="telugu.ttf")
+TAMIL_FONT = Font(font_name="tamil.ttf")
+DEVANAGARI_FONT = Font(font_name="devanagari.ttf")

{paddlex-3.0.2.dist-info → paddlex-3.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: paddlex
-Version: 3.0.2
+Version: 3.1.0
 Summary: Low-code development tool based on PaddlePaddle.
 Home-page: UNKNOWN
 Author: PaddlePaddle Authors
@@ -45,6 +45,7 @@ Requires-Dist: ujson
 Provides-Extra: all
 Requires-Dist: aiohttp>=3.9; extra == "all"
 Requires-Dist: bce-python-sdk>=0.9; extra == "all"
+Requires-Dist: beautifulsoup4; extra == "all"
 Requires-Dist: chinese-calendar; extra == "all"
 Requires-Dist: einops; extra == "all"
 Requires-Dist: faiss-cpu; extra == "all"
@@ -81,6 +82,7 @@ Requires-Dist: uvicorn>=0.16; extra == "all"
 Requires-Dist: yarl>=1.9; extra == "all"
 Requires-Dist: decord==0.6.0; ((platform_machine == "x86_64" or platform_machine == "AMD64") and sys_platform != "darwin") and extra == "all"
 Provides-Extra: base
+Requires-Dist: beautifulsoup4; extra == "base"
 Requires-Dist: chinese-calendar; extra == "base"
 Requires-Dist: einops; extra == "base"
 Requires-Dist: faiss-cpu; extra == "base"
@@ -182,6 +184,20 @@ Requires-Dist: Jinja2; extra == "speech"
 Requires-Dist: regex; extra == "speech"
 Requires-Dist: soundfile; extra == "speech"
 Requires-Dist: tqdm; extra == "speech"
+Provides-Extra: trans
+Requires-Dist: beautifulsoup4; extra == "trans"
+Requires-Dist: ftfy; extra == "trans"
+Requires-Dist: imagesize; extra == "trans"
+Requires-Dist: lxml; extra == "trans"
+Requires-Dist: openai>=1.63; extra == "trans"
+Requires-Dist: opencv-contrib-python==4.10.0.84; extra == "trans"
+Requires-Dist: openpyxl; extra == "trans"
+Requires-Dist: premailer; extra == "trans"
+Requires-Dist: pyclipper; extra == "trans"
+Requires-Dist: pypdfium2>=4; extra == "trans"
+Requires-Dist: scikit-learn; extra == "trans"
+Requires-Dist: shapely; extra == "trans"
+Requires-Dist: tokenizers>=0.19; extra == "trans"
 Provides-Extra: ts
 Requires-Dist: chinese-calendar; extra == "ts"
 Requires-Dist: joblib; extra == "ts"
@@ -228,6 +244,14 @@ PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了
 
 ## 📣 近期更新
 
+🔥🔥 **2025.6.28，发布 PaddleX v3.1.0**，新增能力如下：
+
+- **重要模型：**
+  - **新增PP-OCRv5多语种文本识别模型**，支持法语、西班牙语、葡萄牙语、俄语、韩语等37种语言的文字识别模型的训推流程。**平均精度涨幅超30%。**
+  - 升级PP-StructureV3中的**PP-Chart2Table模型**，图表转表能力进一步升级，在内部自建测评集合上指标（RMS-F1）**提升9.36个百分点（71.24% -> 80.60%）**
+- **重要产线：**
+  - 新增基于PP-StructureV3和ERNIE 4.5 Turbo的**文档翻译产线PP-DocTranslation，支持翻译Markdown文档、各种复杂版式的PDF文档和文档图像，结果保存为Markdown格式文档。**
+
 
 🔥🔥 **2025.5.20，发布 PaddleX v3.0.0**，相比PaddleX v2.x，核心升级如下：