py2ls 0.1.10.23__tar.gz → 0.1.10.24__tar.gz

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.1.10.23
+Version: 0.1.10.24
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/py2ls/ips.py

@@ -1443,10 +1443,21 @@ def fappend(fpath, content=None):
         file.write(content)
 
 
+def filter_kwargs(kws, valid_kwargs):
+    if isinstance(valid_kwargs, dict):
+        kwargs_filtered = {
+            key: value for key, value in kws.items() if key in valid_kwargs.keys()
+        }
+    elif isinstance(valid_kwargs, list):
+        kwargs_filtered = {
+            key: value for key, value in kws.items() if key in valid_kwargs
+        }
+    return kwargs_filtered
+
+
 def fsave(
     fpath,
     content,
-    mode="w",
     how="overwrite",
     kind=None,
     font_name="Times",
@@ -1468,7 +1479,7 @@ def fsave(
         None
     """
 
-    def save_content(fpath, content, mode=mode, how="overwrite"):
+    def save_content(fpath, content, mode="w", how="overwrite"):
         if "wri" in how.lower():
             with open(fpath, mode, encoding="utf-8") as file:
                 file.write(content)
@@ -1515,13 +1526,36 @@ def fsave(
         pdf.output(fpath, "F")
 
     def save_csv(fpath, data, **kwargs):
+        # https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_csv.html
+        kwargs_csv = dict(
+            path_or_buf=None,
+            sep=",",
+            na_rep="",
+            float_format=None,
+            columns=None,
+            header=True,
+            index=True,
+            index_label=None,
+            mode="w",
+            encoding=None,
+            compression="infer",
+            quoting=None,
+            quotechar='"',
+            lineterminator=None,
+            chunksize=None,
+            date_format=None,
+            doublequote=True,
+            escapechar=None,
+            decimal=".",
+            errors="strict",
+            storage_options=None,
+        )
+        kwargs_valid = filter_kwargs(kwargs, kwargs_csv)
         df = pd.DataFrame(data)
-        df.to_csv(fpath, **kwargs)
+        df.to_csv(fpath, **kwargs_valid)
 
     def save_xlsx(fpath, data, **kwargs):
-        format = kwargs.get("format", None)
-        if format:
-            kwargs.pop("format", None)
+        if any(kwargs):
             format_excel(df=data, filename=fpath, **kwargs)
         else:
             kwargs.pop("format", None)
@@ -1618,7 +1652,7 @@ def fsave(
         print(
             f"Warning:\n{kind} is not in the supported list ['docx', 'txt', 'md', 'html', 'pdf', 'csv', 'xlsx', 'json', 'xml', 'yaml']"
         )
-
+    mode = kwargs.get("mode", "w")
     if kind == "docx" or kind == "doc":
         save_docx(fpath, content, font_name, font_size, spacing)
     elif kind == "txt":
@@ -3186,7 +3220,13 @@ def hex2argb(hex_color):
     # Otherwise, assume it's in RRGGBB format and prepend FF for opaque
     if len(hex_color) == 6:
         return f"FF{hex_color}"
-
+    if len(hex_color) == 7:
+        return f"F{hex_color}"
+    else:
+        if len(hex_color) > 8:
+            return hex_color[-9:]
+        else:
+            return "F" * (9 - len(hex_color)) + hex_color
     raise ValueError(
         "Invalid hex color format. Use RRGGBB, #RRGGBB, or aARRGGBB format."
     )
@@ -3540,7 +3580,6 @@ def format_excel(
     number_format=None,  # dict: e.g., {1:"0.00", 2:"#,##0",3:"0%",4:"$#,##0.00"}
     data_validation=None,  # dict
     conditional_format=None,  # dict
-    index_default=False,
     **kwargs,
 ):
     if not isinstance(df, pd.DataFrame):
@@ -3711,15 +3750,29 @@ format_excel(
         print(func_xample)
         return None
     kwargs.pop("format", None)  # 更好地跟fsave结合使用
+    kwargs.pop("sheet_name", None)  # 更好地跟df.to_excel结合使用
+    sheet_name_corr = (
+        sheet_name if isinstance(sheet_name, str) else f"Sheet_{sheet_name}"
+    )
 
-    # Save DataFrame to Excel file
-    if not index_default:
-        df.to_excel(filename, index=False, **kwargs)
-    else:
-        df.to_excel(filename, **kwargs)
+    # 只有openpyxl才支持 append
+    mode = strcmp(kwargs.get("mode", "w"), ["a", "w"])[0]
+    kwargs.pop("mode", None)
+    engine = strcmp(kwargs.get("engine", "openpyxl"), ["xlsxwriter", "openpyxl"])[0]
+    # 通常是不需要保存index的
+    index = kwargs.get("index", False)
+    kwargs.pop("index", None)
+    # save file
+    with pd.ExcelWriter(filename, mode=mode, engine=engine) as writer:
+        df.to_excel(writer, sheet_name=sheet_name_corr, index=index, **kwargs)
 
     wb = load_workbook(filename)
-    ws = wb.worksheets[sheet_name]
+    if isinstance(sheet_name, str):
+        ws = wb[sheet_name]
+    elif isinstance(sheet_name, int):
+        ws = wb.worksheets[sheet_name]
+    else:
+        ws = wb.worksheets[sheet_name]  # the index of worksheets
 
     # !Apply cell formatting
     if cell:
@@ -3812,7 +3865,9 @@ format_excel(
             comment = [comment]
         for comment_ in comment:
             for (row, col), comment_str in comment_.items():
-                ws.cell(row=row, column=col).comment = Comment(comment_str, "Author")
+                ws.cell(row=row + 1, column=col + 1).comment = Comment(
+                    comment_str, "Author"
+                )
 
     # !Add link
     if link:
@@ -3820,7 +3875,7 @@ format_excel(
             link = [link]
         for link_ in link:
             for (row, col), link_str in link_.items():
-                ws.cell(row=row, column=col).hyperlink = link_str
+                ws.cell(row=row + 1, column=col + 1).hyperlink = link_str
 
     # !Apply data validation
     if data_validation:

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/py2ls/netfinder.py

@@ -582,7 +582,7 @@ def find_links(url, driver="request", booster=False):
                 if all(exclusion not in link_href for exclusion in cond_ex):
                     links_href.append(link_href)
 
-        unique_links = list(set(links_href))  # Remove duplicates
+        unique_links = ips.unique(links_href)  # Remove duplicates
 
         if booster:
             for link in unique_links:
@@ -590,7 +590,7 @@ def find_links(url, driver="request", booster=False):
                     sub_links = find_links(link, driver=driver, booster=False)
                     if sub_links:
                         links_href.extend(sub_links)
-            links_href = list(set(links_href))  # Remove duplicates again
+            links_href = ips.unique(links_href)  # Remove duplicates again
 
         return links_href
 

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/py2ls/ocr.py

@@ -286,14 +286,16 @@ def add_text_pil(
     text,
     position,
     font_size=12,
-    color=(255, 0, 0),
-    bg_color=(173, 216, 230, 120),
+    color=(0, 0, 0),
+    bg_color=(133, 203, 245, 100),
 ):
     # Convert the image to PIL format
-    pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
-    # Create a drawing context
-    draw = ImageDraw.Draw(pil_image)
+    pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)).convert("RGBA")
     # Define the font (make sure to use a font that supports Chinese characters)
+    overlay = Image.new("RGBA", pil_image.size, (255, 255, 255, 0))
+    # Create a drawing context
+    draw = ImageDraw.Draw(overlay)
+
     try:
         font = ImageFont.truetype(
             "/System/Library/Fonts/Supplemental/Songti.ttc", font_size
@@ -328,8 +330,14 @@ def add_text_pil(
     draw.rectangle(background_rect, fill=bg_color)
     # Add text to the image
     draw.text(adjusted_position, text, font=font, fill=color)
+    # Ensure both images are in RGBA mode for alpha compositing
+    if pil_image.mode != "RGBA":
+        pil_image = pil_image.convert("RGBA")
+    if overlay.mode != "RGBA":
+        overlay = overlay.convert("RGBA")
+    combined = Image.alpha_composite(pil_image, overlay)
     # Convert the image back to OpenCV format
-    image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGBA2BGR)
+    image = cv2.cvtColor(np.array(combined), cv2.COLOR_RGBA2BGR)
     return image
 
 
@@ -382,12 +390,15 @@ def preprocess_img(
         image = cv2.imread(image)
     if not isinstance(image, np.ndarray):
         image = np.array(image)
-    if image.shape[1] == 4:  # Check if it has an alpha channel
-        # Drop the alpha channel (if needed), or handle it as required
-        image = cv2.cvtColor(image, cv2.COLOR_RGBA2RGB)
-    else:
-        # Convert RGB to BGR for OpenCV compatibility
-        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    try:
+        if image.shape[1] == 4:  # Check if it has an alpha channel
+            # Drop the alpha channel (if needed), or handle it as required
+            image = cv2.cvtColor(image, cv2.COLOR_RGBA2RGB)
+        else:
+            # Convert RGB to BGR for OpenCV compatibility
+            image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    except:
+        pass
 
     # Rotate image
     if rotate == "auto":
@@ -532,7 +543,7 @@ def get_text(
     thr=0.1,
     gpu=True,
     decoder="wordbeamsearch",  #'greedy', 'beamsearch' and 'wordbeamsearch'(hightly accurate)
-    output="all",
+    output="txt",
     preprocess=None,
     postprocess="not ready",
     show=True,
@@ -541,9 +552,9 @@ def get_text(
     font=cv2.FONT_HERSHEY_SIMPLEX,
     font_scale=0.8,
     thickness_text=2,  # Line thickness of 2 px
-    color_box=(0, 255, 0),  # draw_box
-    color_text=(203, 44, 57),  # draw_box
-    bg_color=(173, 216, 230, 128),
+    box_color=(0, 255, 0),  # draw_box
+    font_color=(0, 0, 0),
+    bg_color=(133, 203, 245, 100),
     usage=False,
     **kwargs,
 ):
@@ -559,8 +570,8 @@ def get_text(
     show: 是否显示结果图像。
     ax: 用于显示图像的 Matplotlib 子图。
     cmap: 用于显示图像的颜色映射。
-    color_box: 边界框的颜色。
-    color_text: 文本的颜色。
+    box_color: 边界框的颜色。
+    font_color: 文本的颜色。
     kwargs: 传递给 EasyOCR readtext 函数的其他参数。
 
     # Uage
@@ -632,19 +643,19 @@ def get_text(
                 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.rectangle(image, top_left, bottom_right, box_color, 2)
                     # image = cv2.putText(
-                    #     image, text, top_left, font, font_scale, color_text, thickness_text
+                    #     image, text, top_left, font, font_scale, font_color, thickness_text
                     # )
                     image = add_text_pil(
                         image,
                         text,
                         top_left,
                         font_size=font_scale * 32,
-                        color=color_text,
+                        color=font_color,
                     )
-            img_cmp = cv2.cvtColor(image, cmap)
-            ax.imshow(img_cmp)
+            # img_cmp = cv2.cvtColor(image, cmap)
+            ax.imshow(image)
             ax.axis("off")
             # plt.show()
             # 根据输出类型返回相应的结果
@@ -720,20 +731,20 @@ def get_text(
                         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.rectangle(image, top_left, bottom_right, box_color, 2)
                     # image = cv2.putText(
-                    #     image, text, top_left, font, font_scale, color_text, thickness_text
+                    #     image, text, top_left, font, font_scale, font_color, thickness_text
                     # )
                     image = add_text_pil(
                         image,
                         text,
                         top_left,
                         font_size=font_scale * 32,
-                        color=color_text,
+                        color=font_color,
                         bg_color=bg_color,
                     )
             img_cmp = cv2.cvtColor(image, cmap)
-            ax.imshow(img_cmp)
+            ax.imshow(image)
             ax.axis("off")
             # plt.show()
             # 根据输出类型返回相应的结果
@@ -797,13 +808,13 @@ def get_text(
                     bottom_right = (right, h - bottom)
 
                     # Draw the bounding box
-                    image = cv2.rectangle(image, top_left, bottom_right, color_box, 2)
+                    image = cv2.rectangle(image, top_left, bottom_right, box_color, 2)
                     image = add_text_pil(
                         image,
                         char,
                         left,
                         font_size=font_scale * 32,
-                        color=color_text,
+                        color=font_color,
                     )
             img_cmp = cv2.cvtColor(image, cmap)
             ax.imshow(img_cmp)
@@ -838,8 +849,8 @@ def draw_box(
     detections=None,
     thr=0.25,
     cmap=cv2.COLOR_BGR2RGB,
-    color_box=(0, 255, 0),  # draw_box
-    color_text=(0, 0, 255),  # draw_box
+    box_color=(0, 255, 0),  # draw_box
+    font_color=(0, 0, 255),  # draw_box
     font_scale=0.8,
     show=True,
     ax=None,
@@ -857,12 +868,12 @@ def draw_box(
         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.rectangle(image, top_left, bottom_right, box_color, 2)
             # image = cv2.putText(
-            #     image, text, top_left, font, font_scale, color_text, thickness_text
+            #     image, text, top_left, font, font_scale, font_color, thickness_text
             # )
             image = add_text_pil(
-                image, text, top_left, font_size=font_scale * 32, color=color_text
+                image, text, top_left, font_size=font_scale * 32, color=font_color
             )
 
     img_cmp = cv2.cvtColor(image, cmap)

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/py2ls/plot.py

@@ -2391,3 +2391,49 @@ def style_examples(
             dir_save,
             f"{f.name[i]}.pdf",
         )
+
+
+import matplotlib.pyplot as plt
+from PIL import Image
+
+
+def thumbnail(dir_img_list: list, figsize=(10, 10), dpi=100, show=False, usage=False):
+    """
+    Display a thumbnail figure of all images in the specified directory.
+
+    Args:
+        dir_img_list (list): List of image file paths to display.
+        figsize (tuple): Size of the figure (width, height) in inches.
+        dpi (int): Dots per inch for the figure.
+    """
+    if usage:
+        print(
+            'thumbnail(listdir("./img-innere-medizin-ii", ["jpeg", "jpg", "png"]).fpath.tolist(),figsize=[5,5],dpi=200)'
+        )
+    num_images = len(dir_img_list)
+    if num_images == 0:
+        print("No images found to display.")
+        return None
+
+    # Calculate the number of rows and columns for the grid
+    cols = int(num_images**0.5)
+    rows = (num_images // cols) + (num_images % cols > 0)
+
+    fig, axs = plt.subplots(rows, cols, figsize=figsize, dpi=dpi)
+    axs = axs.flatten()  # Flatten the grid for easy iteration
+
+    for ax, image_file in zip(axs, dir_img_list):
+        try:
+            img = Image.open(image_file)
+            ax.imshow(img)
+            ax.axis("off")  # Hide axes
+        except (IOError, FileNotFoundError) as e:
+            ax.axis("off")  # Still hide axes if image can't be loaded
+
+    # Hide any remaining unused axes
+    for ax in axs[len(dir_img_list) :]:
+        ax.axis("off")
+
+    plt.tight_layout()
+    if show:
+        plt.show()

{py2ls-0.1.10.23 → py2ls-0.1.10.24}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "py2ls"
-version = "0.1.10.23"
+version = "0.1.10.24"
 description = "py(thon)2(too)ls"
 authors = ["Jianfeng <Jianfeng.Liu0413@gmail.com>"]
 readme = "README.md"