PyPI - py2ls - Versions diffs - 0.1.10.3__tar.gz → 0.1.10.4__tar.gz - Mend

py2ls 0.1.10.3tar.gz → 0.1.10.4tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (220) hide show

{py2ls-0.1.10.3 → py2ls-0.1.10.4}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.1.10.3
+Version: 0.1.10.4
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com
@@ -29,8 +29,8 @@ Requires-Dist: Pygments (>=2.18.0)
 Requires-Dist: QtPy (>=2.4.1)
 Requires-Dist: SciencePlots (>=2.1.1)
 Requires-Dist: XlsxWriter (>=3.2.0)
-Requires-Dist: appnope (>=0.1.4)
-Requires-Dist: appscript (>=1.2.5)
+Requires-Dist: appnope (>=0.1.4) ; sys_platform == "darwin"
+Requires-Dist: appscript (>=1.2.5) ; sys_platform == "darwin"
 Requires-Dist: asciitree (>=0.3.3)
 Requires-Dist: asttokens (>=2.4.1)
 Requires-Dist: attrs (>=23.2.0)
@@ -234,7 +234,7 @@ Requires-Dist: websocket-client (>=1.8.0)
 Requires-Dist: wrapt (>=1.16.0)
 Requires-Dist: wsproto (>=1.2.0)
 Requires-Dist: xarray (>=2024.6.0)
-Requires-Dist: xattr (>=0.10.1)
+Requires-Dist: xattr (>=0.10.1) ; sys_platform == "darwin"
 Requires-Dist: zarr (>=2.17.2)
 Description-Content-Type: text/markdown

{py2ls-0.1.10.3 → py2ls-0.1.10.4}/py2ls/batman.py RENAMED Viewed

@@ -11,6 +11,21 @@ from pprint import pp
 import json
+# Helper to convert text or list of text to HTML
+def convert_to_html(text_list):
+    if not isinstance(text_list, list):
+        text_list = [text_list]
+    # Convert each element into HTML and add line breaks
+    html_content = ""  # "<html><body>\n"
+    html_content += "".join(
+        text.replace("\n", "<br>") for text in text_list if text.strip()
+    )
+    # html_content += "\n</body></html>"
+    return html_content
 def extract_kv(
     dir_data="/Users/macjianfeng/Dropbox/github/python/py2ls/confidential_data/gmail_login.json",
     idx=0,
@@ -36,14 +51,18 @@ def email_to(**kwargs):
     :param what: Email what
     :param attachments: List of file paths to attach
     """
-    who, what, subject = None, None, None
+    who, what, subject, signature = None, None, None, None
     attachments = False
     pause_sec = False  # default 10 seconds pause
     signature_styles = extract_kv(idx=1)[1]  # signature list
     signature = signature_styles[0]  # default signature,None
     verbose = True
+    if not kwargs:
+        print(
+            f'\nUsage:\nemail_to(who="example@gmail.com",\n         subject="test",\n         what="this is the body",\n         attachments="/Users/test.pdf"\n         )'
+        )
+        return None
     # params config
     for k, v in kwargs.items():
         if any(
@@ -80,15 +99,26 @@ def email_to(**kwargs):
     message["To"] = who
     message["Subject"] = subject
-    # add signature
-    if signature:
-        what += f"\n\n{signature}\n"
     # the eamil's body
-    message.attach(MIMEText(what, "plain"))
+    if what is None:
+        what = ""
+    if isinstance(what, list):
+        what = convert_to_html(what)
+    if 'class="dataframe"' in str(attachments):
+        # Combine HTML content correctly
+        html_content = "<html><body>\n"
+        html_content += f"{convert_to_html(what)}<br>{attachments}"
+        html_content += f"<br><br>{convert_to_html([signature])}"
+        html_content += "\n</body></html>"
+        message.attach(MIMEText(html_content, "html"))
+    else:
+        # add signature
+        if signature:
+            what += f"\n\n{signature}\n"
+        message.attach(MIMEText(what, "plain"))
     # attach files
-    if attachments:
+    if attachments and not 'class="dataframe"' in str(attachments):
         if isinstance(attachments, str):
             attachments = [attachments]
         for file in attachments:

{py2ls-0.1.10.3 → py2ls-0.1.10.4}/py2ls/ocr.py RENAMED Viewed

@@ -12,6 +12,12 @@ import re
 from PIL import Image, ImageDraw, ImageFont
 import PIL.PngImagePlugin
 import pytesseract
+from paddleocr import PaddleOCR
+import logging
+logging.getLogger("ppocr").setLevel(
+    logging.WARNING
+)  # or logging.ERROR to show only error messages
 """
     Optical Character Recognition (OCR)
@@ -31,6 +37,25 @@ lang_valid = {
         "kannada": "kn",
         "german": "de",
     },
+    "paddleocr": {
+        "chinese": "ch",
+        "chinese_traditional": "chinese_cht",
+        "english": "en",
+        "french": "fr",
+        "german": "de",
+        "korean": "korean",
+        "japanese": "japan",
+        "russian": "ru",
+        "italian": "it",
+        "portuguese": "pt",
+        "spanish": "es",
+        "polish": "pl",
+        "dutch": "nl",
+        "arabic": "ar",
+        "vietnamese": "vi",
+        "tamil": "ta",
+        "turkish": "tr",
+    },
     "pytesseract": {
         "afrikaans": "afr",
         "amharic": "amh",
@@ -133,6 +158,8 @@ def lang_auto_detect(
     lang,
     model="easyocr",  # "easyocr" or "pytesseract"
 ):
+    models = ["easyocr", "paddleocr", "pytesseract"]
+    model = strcmp(model, models)[0]
     res_lang = []
     if isinstance(lang, str):
         lang = [lang]
@@ -254,7 +281,14 @@ def undistort_image(image, camera_matrix, dist_coeffs):
     return cv2.undistort(image, camera_matrix, dist_coeffs)
-def add_text_pil(image, text, position, font_size=10, color=(255, 0, 0)):
+def add_text_pil(
+    image,
+    text,
+    position,
+    font_size=12,
+    color=(255, 0, 0),
+    bg_color=(173, 216, 230, 120),
+):
     # Convert the image to PIL format
     pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
     # Create a drawing context
@@ -270,17 +304,32 @@ def add_text_pil(image, text, position, font_size=10, color=(255, 0, 0)):
     # cal top_left position
     # Measure text size using textbbox
     text_bbox = draw.textbbox((0, 0), text, font=font)
+    # # 或者只画 text, # Calculate text size
+    # text_width, text_height = draw.textsize(text, font=font)
     text_width = text_bbox[2] - text_bbox[0]
     text_height = text_bbox[3] - text_bbox[1]
+    # Draw background rectangle
+    x, y = position
     # Calculate 5% of the text height for upward adjustment
-    offset = int(0.5 * text_height)  # 上移动 50%
+    offset = int(
+        0.1 * text_height
+    )  # 这就不再上移动了; # int(0.5 * text_height)  # 上移动 50%
     # Adjust position to match OpenCV's bottom-left alignment
     adjusted_position = (position[0], position[1] - text_height - offset)
+    background_rect = [
+        adjusted_position[0],
+        adjusted_position[1],
+        x + text_width,
+        y + text_height,
+    ]
+    draw.rectangle(background_rect, fill=bg_color)
     # Add text to the image
     draw.text(adjusted_position, text, font=font, fill=color)
     # Convert the image back to OpenCV format
-    image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
+    image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGBA2BGR)
     return image
@@ -479,8 +528,8 @@ def text_postprocess(
 def get_text(
     image,
     lang=["ch_sim", "en"],
-    model="easyocr",  # "pytesseract"
-    thr=0.25,
+    model="paddleocr",  # "pytesseract","paddleocr","easyocr"
+    thr=0.1,
     gpu=True,
     decoder="wordbeamsearch",  #'greedy', 'beamsearch' and 'wordbeamsearch'(hightly accurate)
     output="all",
@@ -493,7 +542,9 @@ def get_text(
     font_scale=0.8,
     thickness_text=2,  # Line thickness of 2 px
     color_box=(0, 255, 0),  # draw_box
-    color_text=(0, 0, 255),  # draw_box
+    color_text=(203, 44, 57),  # draw_box
+    bg_color=(173, 216, 230, 128),
+    usage=False,
     **kwargs,
 ):
     """
@@ -513,34 +564,38 @@ def get_text(
     kwargs: 传递给 EasyOCR readtext 函数的其他参数。
     # Uage
-    image_path = 'car_plate.jpg'  # 替换为你的图像路径
-    results = get_text(
-        image_path,
-        lang=["en"],
-        gpu=False,
-        output="text",
-        preprocess={
-            "grayscale": True,
-            "threshold": True,
-            "threshold_method": 'adaptive',
-            "denoise": True,
-            "blur_ksize": (5, 5),
-            "morph": True,
-            "morph_op": 'close',
-            "morph_kernel_size": (3, 3),
-            "enhance_contrast": True,
-            "clahe_clip": 2.0,
-            "clahe_grid_size": (8, 8),
-            "edge_detection": False
-        },
-        adjust_contrast=0.7
-    )
     """
+    if usage:
+        print(
+            """
+        image_path = 'car_plate.jpg'  # 替换为你的图像路径
+        results = get_text(
+            image_path,
+            lang=["en"],
+            gpu=False,
+            output="text",
+            preprocess={
+                "grayscale": True,
+                "threshold": True,
+                "threshold_method": 'adaptive',
+                "blur": True,
+                "blur_ksize": (5, 5),
+                "morph": True,
+                "morph_op": 'close',
+                "morph_kernel_size": (3, 3),
+                "enhance_contrast": True,
+                "clahe_clip": 2.0,
+                "clahe_grid_size": (8, 8),
+                "edge_detection": False
+            },
+            adjust_contrast=0.7
+        )
+    """
+        )
-    if ax is None:
-        ax = plt.gca()
+    models = ["easyocr", "paddleocr", "pytesseract"]
+    model = strcmp(model, models)[0]
     lang = lang_auto_detect(lang, model)
-    print(f"detecting language(s):{lang}")
     if isinstance(image, str):
         image = cv2.imread(image)
@@ -553,6 +608,7 @@ def get_text(
         preprocess = {}
     image_process = preprocess_img(image, **preprocess)
     if "easy" in model.lower():
+        print(f"detecting language(s):{lang}")
         # Perform OCR on the image
         reader = easyocr.Reader(lang, gpu=gpu)
         detections = reader.readtext(image_process, decoder=decoder, **kwargs)
@@ -565,12 +621,104 @@ def get_text(
                 merge=True,
             )
             text_corr = []
-            for _, text, _ in detections:
+            [
+                text_corr.extend(text_postprocess(text, **postprocess))
+                for _, text, _ in detections
+            ]
+        if show:
+            if ax is None:
+                ax = plt.gca()
+            for bbox, text, score in detections:
+                if score > thr:
+                    top_left = tuple(map(int, bbox[0]))
+                    bottom_right = tuple(map(int, bbox[2]))
+                    image = cv2.rectangle(image, top_left, bottom_right, color_box, 2)
+                    # image = cv2.putText(
+                    #     image, text, top_left, font, font_scale, color_text, thickness_text
+                    # )
+                    image = add_text_pil(
+                        image,
+                        text,
+                        top_left,
+                        font_size=font_scale * 32,
+                        color=color_text,
+                    )
+            img_cmp = cv2.cvtColor(image, cmap)
+            ax.imshow(img_cmp)
+            ax.axis("off")
+            # plt.show()
+            # 根据输出类型返回相应的结果
+            if output == "all":
+                return ax, detections
+            elif "t" in output.lower() and "x" in output.lower():
+                # 提取文本，过滤低置信度的结果
+                text = [text_ for _, text_, score_ in detections if score_ >= thr]
+                if postprocess:
+                    return ax, text
+                else:
+                    return text_corr
+            elif "score" in output.lower() or "prob" in output.lower():
+                # 提取分数
+                scores = [score_ for _, _, score_ in detections]
+                return ax, scores
+            elif "box" in output.lower():
+                # 提取边界框，过滤低置信度的结果
+                bboxes = [bbox_ for bbox_, _, score_ in detections if score_ >= thr]
+                return ax, bboxes
+            else:
+                # 默认返回所有检测信息
+                return ax, detections
+        else:
+            # 根据输出类型返回相应的结果
+            if output == "all":
+                return detections
+            elif "t" in output.lower() and "x" in output.lower():
+                # 提取文本，过滤低置信度的结果
+                text = [text_ for _, text_, score_ in detections if score_ >= thr]
+                return text
+            elif "score" in output.lower() or "prob" in output.lower():
+                # 提取分数
+                scores = [score_ for _, _, score_ in detections]
+                return scores
+            elif "box" in output.lower():
+                # 提取边界框，过滤低置信度的结果
+                bboxes = [bbox_ for bbox_, _, score_ in detections if score_ >= thr]
+                return bboxes
+            else:
+                # 默认返回所有检测信息
+                return detections
+    elif "pad" in model.lower():
+        ocr = PaddleOCR(
+            use_angle_cls=True,
+            cls=True,
+        )  # PaddleOCR supports only one language at a time
+        result = ocr.ocr(image_process, **kwargs)
+        detections = []
+        for line in result[0]:
+            bbox, (text, score) = line
+            detections.append((bbox, text, score))
+        if postprocess is None:
+            postprocess = dict(
+                spell_check=True,
+                clean=True,
+                filter=dict(min_length=2),
+                pattern=None,
+                merge=True,
+            )
+            text_corr = []
+            [
                 text_corr.extend(text_postprocess(text, **postprocess))
+                for _, text, _ in detections
+            ]
         if show:
+            if ax is None:
+                ax = plt.gca()
             for bbox, text, score in detections:
                 if score > thr:
                     top_left = tuple(map(int, bbox[0]))
+                    bottom_left = tuple(
+                        map(int, bbox[1])
+                    )  # Bottom-left for more accurate placement
                     bottom_right = tuple(map(int, bbox[2]))
                     image = cv2.rectangle(image, top_left, bottom_right, color_box, 2)
                     # image = cv2.putText(
@@ -582,6 +730,7 @@ def get_text(
                         top_left,
                         font_size=font_scale * 32,
                         color=color_text,
+                        bg_color=bg_color,
                     )
             img_cmp = cv2.cvtColor(image, cmap)
             ax.imshow(img_cmp)
@@ -627,7 +776,10 @@ def get_text(
             else:
                 # 默认返回所有检测信息
                 return detections
     else:  # "pytesseract"
+        if ax is None:
+            ax = plt.gca()
         text = pytesseract.image_to_string(image_process, lang="+".join(lang), **kwargs)
         bboxes = pytesseract.image_to_boxes(image_process, **kwargs)
         if show:
@@ -649,7 +801,7 @@ def get_text(
                     image = add_text_pil(
                         image,
                         char,
-                        top_left,
+                        left,
                         font_size=font_scale * 32,
                         color=color_text,
                     )

{py2ls-0.1.10.3 → py2ls-0.1.10.4}/pyproject.toml RENAMED Viewed

@@ -1,14 +1,14 @@
 [tool.poetry]
 name = "py2ls"
-version = "0.1.10.3"
+version = "0.1.10.4"
 description = "py(thon)2(too)ls"
 authors = ["Jianfeng <Jianfeng.Liu0413@gmail.com>"]
 readme = "README.md"
 [tool.poetry.dependencies]
 python = "^3.10"
-appnope = ">=0.1.4"
-appscript = ">=1.2.5"
+appnope = { version = ">=0.1.4", markers = "sys_platform == 'darwin'" }
+appscript = { version = ">=1.2.5", markers = "sys_platform == 'darwin'" }
 asciitree = ">=0.3.3"
 asttokens = ">=2.4.1"
 attrs = ">=23.2.0"
@@ -231,7 +231,9 @@ websocket-client = ">=1.8.0"
 wrapt = ">=1.16.0"
 wsproto = ">=1.2.0"
 xarray = ">=2024.6.0"
-xattr = ">=0.10.1"
+xattr = { version = ">=0.10.1", markers = "sys_platform == 'darwin'" }
 XlsxWriter = ">=3.2.0"
 zarr = ">=2.17.2"