table-renderer 0.1.1__tar.gz → 0.3.0__tar.gz

{table_renderer-0.1.1 → table_renderer-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: table-renderer
-Version: 0.1.1
+Version: 0.3.0
 Summary: A Python library for rendering structured tables as high-quality images or HTML.
 Keywords: table,renderer,rendering,image,html,weasyprint,pdfium,report
 Author: pTaunium
@@ -42,6 +42,7 @@ Description-Content-Type: text/markdown
 - **Business Friendly**: Uses `pypdfium2` (Apache-2.0) and `WeasyPrint` for a 100% MIT-compatible dependency chain.
 - **High-Quality Rendering**: Powered by WeasyPrint (CSS engine), supporting complex text wrapping, alignment, and cell merging.
 - **Auto-Crop**: Automatically crops images to the actual table area using visual detection, eliminating unnecessary white space.
+- **Continuous Long Tables**: Automatically stitches multiple PDF pages into a single continuous long image, preventing content from being cut off.
 - **Object-Oriented API**: Clean `Table` -> `Row/Column` -> `Cell` hierarchy with fluent interface support.
 - **Cascading Styles**: Manage visual styles effortlessly with "Global Defaults + Local Overrides."
 - **Multi-language Font Support**: Support for font stacks (e.g., different fonts for English and Chinese).
@@ -82,7 +83,7 @@ from table_renderer import Table
 # 1. Initialize a 3x3 table
 table = Table(3, 3)
 table.set_width(600)
-table.set_border(1, "black", "solid")
+table.set_border(width=1, color="black", style="solid")
 
 # 2. Set header style (Row 0)
 header = table.get_row(0)
@@ -156,6 +157,15 @@ table.get_column(0).set_width(200)    # Fixed 200px
 table.get_column(1).set_width("auto") # Distribute remaining space
 ```
 
+**Handling Extremely Wide Tables:**
+The library dynamically estimates canvas width to prevent clipping. However, if your table contains unbreakable strings (like long URLs) and relies purely on auto-layout, you can manually override the canvas width. The auto-crop feature will automatically trim any excess white space.
+
+```python
+# Force a massive canvas width; auto-crop will cleanly trim the excess
+table.set_width(15000)
+table.to_image("wide_table.png")
+```
+
 ### 5. DPI, Formats & Padding
 
 Fine-tune your output image quality and margins.
@@ -164,6 +174,9 @@ Fine-tune your output image quality and margins.
 # High-res JPG with custom 20px padding
 table.to_image("output.jpg", dpi=300, padding=20)
 
+# PNG with a solid white background (instead of the default transparent)
+table.to_image("output_white.png", background_color="white")
+
 # Lightweight WebP with tight margins
 table.to_image("output.webp", dpi=72, padding=0)
 ```
@@ -180,9 +193,8 @@ FROM python:3.12-slim
 # Install system dependencies for WeasyPrint rendering and fonts
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libpango-1.0-0 \
-    libharfbuzz0b \
     libpangoft2-1.0-0 \
-    libpangocairo-1.0-0 \
+    libharfbuzz-subset0 \
     fonts-noto-cjk \
     && rm -rf /var/lib/apt/lists/*
 

{table_renderer-0.1.1 → table_renderer-0.3.0}/README.md

@@ -19,6 +19,7 @@
 - **Business Friendly**: Uses `pypdfium2` (Apache-2.0) and `WeasyPrint` for a 100% MIT-compatible dependency chain.
 - **High-Quality Rendering**: Powered by WeasyPrint (CSS engine), supporting complex text wrapping, alignment, and cell merging.
 - **Auto-Crop**: Automatically crops images to the actual table area using visual detection, eliminating unnecessary white space.
+- **Continuous Long Tables**: Automatically stitches multiple PDF pages into a single continuous long image, preventing content from being cut off.
 - **Object-Oriented API**: Clean `Table` -> `Row/Column` -> `Cell` hierarchy with fluent interface support.
 - **Cascading Styles**: Manage visual styles effortlessly with "Global Defaults + Local Overrides."
 - **Multi-language Font Support**: Support for font stacks (e.g., different fonts for English and Chinese).
@@ -59,7 +60,7 @@ from table_renderer import Table
 # 1. Initialize a 3x3 table
 table = Table(3, 3)
 table.set_width(600)
-table.set_border(1, "black", "solid")
+table.set_border(width=1, color="black", style="solid")
 
 # 2. Set header style (Row 0)
 header = table.get_row(0)
@@ -133,6 +134,15 @@ table.get_column(0).set_width(200)    # Fixed 200px
 table.get_column(1).set_width("auto") # Distribute remaining space
 ```
 
+**Handling Extremely Wide Tables:**
+The library dynamically estimates canvas width to prevent clipping. However, if your table contains unbreakable strings (like long URLs) and relies purely on auto-layout, you can manually override the canvas width. The auto-crop feature will automatically trim any excess white space.
+
+```python
+# Force a massive canvas width; auto-crop will cleanly trim the excess
+table.set_width(15000)
+table.to_image("wide_table.png")
+```
+
 ### 5. DPI, Formats & Padding
 
 Fine-tune your output image quality and margins.
@@ -141,6 +151,9 @@ Fine-tune your output image quality and margins.
 # High-res JPG with custom 20px padding
 table.to_image("output.jpg", dpi=300, padding=20)
 
+# PNG with a solid white background (instead of the default transparent)
+table.to_image("output_white.png", background_color="white")
+
 # Lightweight WebP with tight margins
 table.to_image("output.webp", dpi=72, padding=0)
 ```
@@ -157,9 +170,8 @@ FROM python:3.12-slim
 # Install system dependencies for WeasyPrint rendering and fonts
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libpango-1.0-0 \
-    libharfbuzz0b \
     libpangoft2-1.0-0 \
-    libpangocairo-1.0-0 \
+    libharfbuzz-subset0 \
     fonts-noto-cjk \
     && rm -rf /var/lib/apt/lists/*
 

{table_renderer-0.1.1 → table_renderer-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "table-renderer"
-version = "0.1.1"
+version = "0.3.0"
 description = "A Python library for rendering structured tables as high-quality images or HTML."
 readme = "README.md"
 license = "MIT"

{table_renderer-0.1.1 → table_renderer-0.3.0}/src/table_renderer/__init__.py

@@ -6,6 +6,6 @@ try:
     __version__ = importlib.metadata.version("table-renderer")
 except importlib.metadata.PackageNotFoundError:
     # Package is not installed (e.g. during local development without pip install -e .)
-    __version__ = "0.1.1"
+    __version__ = "0.3.0"
 
 __all__ = ["Cell", "Column", "Row", "Style", "StyledObject", "Table", "__version__"]

{table_renderer-0.1.1 → table_renderer-0.3.0}/src/table_renderer/models/base.py

@@ -12,6 +12,7 @@ class StyledObject:
 
     def set_font(
         self,
+        *,
         size: int | None = None,
         color: str | None = None,
         family: str | None = None,
@@ -50,6 +51,7 @@ class StyledObject:
 
     def set_align(
         self,
+        *,
         horizontal: Literal["left", "center", "right"] | None = None,
         vertical: Literal["top", "middle", "bottom"] | None = None,
     ) -> Self:
@@ -69,6 +71,7 @@ class StyledObject:
 
     def set_border(
         self,
+        *,
         width: int | None = None,
         color: str | None = None,
         style: Literal["solid", "dashed", "dotted"] | None = None,

{table_renderer-0.1.1 → table_renderer-0.3.0}/src/table_renderer/models/cell.py

@@ -38,7 +38,7 @@ class Cell(StyledObject):
         return self
 
     def set_image(
-        self, path: str, width: int | None = None, height: int | None = None
+        self, path: str, *, width: int | None = None, height: int | None = None
     ) -> Self:
         """
         Set an image to be displayed in the cell.
@@ -56,7 +56,7 @@ class Cell(StyledObject):
         self.image_height = height
         return self
 
-    def span(self, rows: int = 1, cols: int = 1) -> Self:
+    def span(self, *, rows: int = 1, cols: int = 1) -> Self:
         """
         Set the row and column span for merging.
 

{table_renderer-0.1.1 → table_renderer-0.3.0}/src/table_renderer/models/table.py

@@ -25,7 +25,7 @@ class Table(StyledObject):
         self._cells = [[Cell() for _ in range(cols)] for _ in range(rows)]
         self._row_objects = [Row(i) for i in range(rows)]
         self._col_objects = [Column(i) for i in range(cols)]
-        self.width: int | str = "100%"
+        self.width: int | str = "auto"
         self.font_files: list[str] = []
 
     def cell(self, row_index: int, col_index: int) -> Cell:
@@ -112,7 +112,14 @@ class Table(StyledObject):
         self.font_files.append(font_path)
         return self
 
-    def to_image(self, output_path: str, dpi: int = 144, padding: int = 10) -> None:
+    def to_image(
+        self,
+        output_path: str,
+        *,
+        dpi: int = 144,
+        padding: int = 10,
+        background_color: str = "transparent",
+    ) -> None:
         """
         Render the table to an image file.
 
@@ -120,17 +127,27 @@ class Table(StyledObject):
             output_path: Path to the output file (e.g., 'table.png', 'table.webp').
             dpi: Resolution of the output image.
             padding: Padding around the table in pixels.
+            background_color: Background color of the image.
         """
-        render_to_image(self, output_path, dpi=dpi, padding=padding)
+        render_to_image(
+            self,
+            output_path,
+            dpi=dpi,
+            padding=padding,
+            background_color=background_color,
+        )
 
-    def to_html(self, output_path: str) -> None:
+    def to_html(
+        self, output_path: str, *, background_color: str = "transparent"
+    ) -> None:
         """
         Export the table to an HTML file.
 
         Args:
             output_path: Path to the output HTML file.
+            background_color: Background color of the HTML body.
         """
-        save_html(self, output_path)
+        save_html(self, output_path, background_color=background_color)
 
     def _prepare_render(self) -> None:
         """Handle merging logic and cascading styles before rendering."""

{table_renderer-0.1.1 → table_renderer-0.3.0}/src/table_renderer/renderer.py

@@ -13,12 +13,13 @@ HTML_TEMPLATE = """
 <head>
 <style>
 @page {
+    size: {{ page_width }}px {{ page_height }}px; /* Dynamically estimated size */
     margin: 0;
 }
 body {
     margin: 0;
     padding: 20px;
-    background-color: transparent;
+    background-color: {{ background_color }};
 }
 {% for font in font_faces %}
 @font-face {
@@ -36,7 +37,14 @@ table {
 td {
     padding: 8px;
     box-sizing: border-box;
+    {{ table_style }}
+}
+
+{% for row in rows %}
+.row-{{ row.index }} {
+    {{ row.style }}
 }
+{% endfor %}
 
 {% for col in columns %}
 .col-{{ col.index }} {
@@ -44,12 +52,6 @@ td {
     {{ col.style }}
 }
 {% endfor %}
-
-{% for row in rows %}
-.row-{{ row.index }} {
-    {{ row.style }}
-}
-{% endfor %}
 </style>
 </head>
 <body>
@@ -59,10 +61,10 @@ td {
             {% for c_idx in range(cells[r_idx]|length) %}
                 {% set cell = cells[r_idx][c_idx] %}
                 {% if not cell.is_merged %}
-                <td class="col-{{ c_idx }}"
+                <td class="row-{{ r_idx }} col-{{ c_idx }}"
                     rowspan="{{ cell.row_span }}"
                     colspan="{{ cell.col_span }}"
-                    style="{{ cell.final_style }}">
+                    style="{{ cell.style.to_css() }}">
                     {% if cell.image_url %}
                     <img src="{{ cell.image_url }}"
                          style="{% if cell.image_width %}width: {{ cell.image_width }}px;{% endif %}
@@ -81,12 +83,13 @@ td {
 """
 
 
-def render_to_html(table: "Table") -> str:
+def render_to_html(table: "Table", *, background_color: str = "transparent") -> str:
     """
     Generate the HTML representation of the table.
 
     Args:
         table: The Table object to render.
+        background_color: The background color of the body.
 
     Returns:
         A string containing the complete HTML document.
@@ -106,12 +109,6 @@ def render_to_html(table: "Table") -> str:
         row_data = []
         for col_index in range(len(table._cells[0])):
             cell = table._cells[row_index][col_index]
-            row = table.get_row(row_index)
-            col = table.get_column(col_index)
-
-            # Cascading: Table -> Row/Col -> Cell
-            base_style = table.style.merge(col.style).merge(row.style)
-            final_style = base_style.merge(cell.style)
 
             # Handle Image URL resolution
             cell.image_url = ""
@@ -122,13 +119,33 @@ def render_to_html(table: "Table") -> str:
                     abs_img_path = os.path.abspath(cell.image_path)
                     cell.image_url = f"file://{abs_img_path}"
 
-            # Attach final style string for template
-            cell.final_style = final_style.to_css()
             row_data.append(cell)
         cells_data.append(row_data)
 
+    # Estimate safe canvas width to prevent clipping
+    # Base it on the number of columns if explicit widths aren't provided (assume ~100px min per column)
+    col_count = len(table._cells[0]) if table._cells else 0
+    estimated_width = max(2000, col_count * 100)
+
+    if isinstance(table.width, int):
+        estimated_width = max(estimated_width, table.width + 100)
+
+    col_width_sum = 0
+    for c in table._col_objects:
+        if isinstance(c.width, int):
+            col_width_sum += c.width
+    estimated_width = max(estimated_width, col_width_sum + 100)
+
+    # Estimate safe canvas height to optimize rendering speed for small tables, capped at 5000px
+    # Assume a generous average of 40px per row plus 100px padding
+    estimated_height = len(table._cells) * 40 + 100
+    estimated_height = min(max(estimated_height, 500), 5000)
+
     template = Template(HTML_TEMPLATE)
     return template.render(
+        page_width=estimated_width,
+        page_height=estimated_height,
+        background_color=background_color,
         table_width=f"{table.width}px" if isinstance(table.width, int) else table.width,
         table_style=table.style.to_css(),
         font_faces=font_faces,
@@ -150,8 +167,10 @@ def render_to_html(table: "Table") -> str:
 def render_to_image(
     table: "Table",
     output_path: str,
+    *,
     dpi: int = 144,
     padding: int = 10,
+    background_color: str = "transparent",
 ) -> None:
     """
     Render the table to an image file.
@@ -161,8 +180,9 @@ def render_to_image(
         output_path: Destination path for the image.
         dpi: Target resolution.
         padding: Margin around the table.
+        background_color: Background color of the image.
     """
-    html_content = render_to_html(table)
+    html_content = render_to_html(table, background_color=background_color)
     # WeasyPrint v53+ removed write_png, so we render to PDF then convert to PNG
     pdf_bytes = HTML(string=html_content).write_pdf()
 
@@ -171,29 +191,45 @@ def render_to_image(
 
     # Load the PDF from bytes
     with pdfium.PdfDocument(pdf_bytes) as pdf:
-        page = pdf[0]
-
-        # Render page to a bitmap
-        # scale_factor: 72 is the default PDF DPI
+        page_images = []
         scale_factor = dpi / 72
-        bitmap = page.render(scale=scale_factor)
 
-        # Convert pdfium bitmap to Pillow Image
-        pil_image = bitmap.to_pil()
-        bitmap.close()
+        # Render each page to a PIL Image
+        for page in pdf:
+            # fill_color=(255, 255, 255, 0) ensures the background is transparent
+            bitmap = page.render(scale=scale_factor, fill_color=(255, 255, 255, 0))
+            pil_page = bitmap.to_pil()
+            page_images.append(pil_page)
+            bitmap.close()
+
+        if not page_images:
+            return
+
+        # Stitch all pages vertically into one long image
+        total_width = max(img.width for img in page_images)
+        total_height = sum(img.height for img in page_images)
+
+        # Create a large canvas
+        pil_image = Image.new("RGBA", (total_width, total_height), (255, 255, 255, 0))
+        y_offset = 0
+        for img in page_images:
+            pil_image.paste(img, (0, y_offset))
+            y_offset += img.height
 
     # Visual Auto-Crop: Find the bounding box of non-white pixels
-    # 1. Convert to RGB to ensure we have a standard background to check
-    bg = Image.new("RGB", pil_image.size, (255, 255, 255))
+    # Use 'L' (grayscale) mode to reduce memory usage (1 byte per pixel vs 3)
     if pil_image.mode == "RGBA":
-        bg.paste(pil_image, mask=pil_image.split()[3])
+        # Flatten RGBA onto a white grayscale background
+        grayscale = Image.new("L", pil_image.size, 255)
+        grayscale.paste(pil_image.convert("L"), mask=pil_image.getchannel("A"))
     else:
-        bg.paste(pil_image)
+        # For RGB or other modes, just convert to grayscale
+        grayscale = pil_image.convert("L")
 
-    # 2. Invert and find bbox of "ink"
+    # Invert and find bbox of "ink" (non-white pixels)
     import PIL.ImageOps
 
-    inverted = PIL.ImageOps.invert(bg)
+    inverted = PIL.ImageOps.invert(grayscale)
     bbox = inverted.getbbox()
 
     if bbox:
@@ -206,17 +242,26 @@ def render_to_image(
         pil_image = pil_image.crop((left, top, right, bottom))
 
     # Save to the requested format (Pillow handles most formats)
+    if output_path.lower().endswith((".jpg", ".jpeg")) and pil_image.mode == "RGBA":
+        # Create a white background image and paste the RGBA image on it to flatten it
+        rgb_image = Image.new("RGB", pil_image.size, (255, 255, 255))
+        rgb_image.paste(pil_image, mask=pil_image.split()[3])
+        pil_image = rgb_image
+
     pil_image.save(output_path)
 
 
-def save_html(table: "Table", output_path: str) -> None:
+def save_html(
+    table: "Table", output_path: str, *, background_color: str = "transparent"
+) -> None:
     """
     Save the table's HTML representation to a file.
 
     Args:
         table: The Table object to export.
         output_path: Path to the destination HTML file.
+        background_color: Background color of the HTML body.
     """
-    html_content = render_to_html(table)
+    html_content = render_to_html(table, background_color=background_color)
     with open(output_path, "w", encoding="utf-8") as f:
         f.write(html_content)