opendataloader-pdf 1.0.5__py3-none-any.whl → 1.1.0__py3-none-any.whl

opendataloader_pdf/__init__.py

@@ -1,3 +1,3 @@
-from .wrapper import run
+from .wrapper import run, convert
 
-__all__ = ["run"]
+__all__ = ["run", "convert"]

opendataloader_pdf/__main__.py

@@ -0,0 +1,5 @@
+from .wrapper import main
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

opendataloader_pdf/wrapper.py

@@ -1,8 +1,9 @@
+import argparse
 import subprocess
 import sys
-import importlib.resources as importlib_resources
-import locale
+import importlib.resources as resources
 from pathlib import Path
+from typing import List, Optional
 
 # The consistent name of the JAR file bundled with the package
 _JAR_NAME = "opendataloader-pdf-cli.jar"
@@ -40,9 +41,6 @@ def run(
         no_json: If True, disable the JSON output.
         debug: If True, prints all messages from the CLI to the console during execution.
 
-    Returns:
-        The stdout from the CLI tool if successful.
-
     Raises:
         FileNotFoundError: If the 'java' command is not found or input_path is invalid.
         subprocess.CalledProcessError: If the CLI tool returns a non-zero exit code.
@@ -51,6 +49,7 @@ def run(
         raise FileNotFoundError(f"Input file or folder not found: {input_path}")
 
     args = []
+    args.append(input_path)
     if output_folder:
         args.extend(["--output-dir", output_folder])
     if password:
@@ -74,49 +73,94 @@ def run(
     if no_json:
         args.append("--no-json")
 
-    args.append(input_path)
+    # Run the command
+    run_jar(args, quiet=not debug)
+
+
+def convert(
+    input_path: List[str],
+    output_dir: Optional[str] = None,
+    password: Optional[str] = None,
+    format: Optional[List[str]] = None,
+    quiet: bool = False,
+    content_safety_off: Optional[List[str]] = None,
+    keep_line_breaks: bool = False,
+    replace_invalid_chars: Optional[str] = None,
+) -> None:
+    """
+    Convert PDF(s) into the requested output format(s).
+
+    Args:
+        input_path: One or more input PDF file paths or directories
+        output_dir: Directory where outputs are written
+        password: Password for encrypted PDFs
+        format: List of output formats (e.g., ["json", "html"])
+        quiet: Suppress CLI logging output
+        content_safety_off: List of content safety filters to disable
+        keep_line_breaks: Preserve line breaks in text output
+        replace_invalid_chars: Replacement character for invalid/unrecognized characters
+    """
+    args: List[str] = []
+    args.extend(input_path)
+    if output_dir:
+        args.extend(["--output-dir", output_dir])
+    if password:
+        args.extend(["--password", password])
+    if format:
+        args.extend(["--format", *format])
+    if quiet:
+        args.append("--quiet")
+    if content_safety_off:
+        args.extend(["--content-safety-off", *content_safety_off])
+    if keep_line_breaks:
+        args.append("--keep-line-breaks")
+    if replace_invalid_chars:
+        args.extend(["--replace-invalid-chars", replace_invalid_chars])
+
+    # Run the command
+    run_jar(args, quiet)
+
 
+def run_jar(args: List[str], quiet: bool = False) -> str:
+    """Run the opendataloader-pdf JAR with the given arguments."""
     try:
-        # Find the JAR file within the package
-        jar_ref = importlib_resources.files("opendataloader_pdf").joinpath(
-            "jar", _JAR_NAME
-        )
-        with importlib_resources.as_file(jar_ref) as jar_path:
-            command = ["java", "-jar", str(jar_path)] + args
+        # Access the embedded JAR inside the package
+        jar_ref = resources.files("opendataloader_pdf").joinpath("jar", _JAR_NAME)
+        with resources.as_file(jar_ref) as jar_path:
+            command = ["java", "-jar", str(jar_path), *args]
 
-            if debug:
-                process = subprocess.Popen(
+            if quiet:
+                # Quiet mode → capture all output
+                result = subprocess.run(
                     command,
-                    stdout=subprocess.PIPE,
-                    stderr=subprocess.STDOUT,
+                    capture_output=True,
                     text=True,
-                    encoding=locale.getpreferredencoding(False),
+                    check=True,
+                    encoding="utf-8",
                 )
+                return result.stdout
 
-                output_lines = []
-                for line in iter(process.stdout.readline, ""):
+            # Streaming mode → live output
+            with subprocess.Popen(
+                command,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.STDOUT,
+                text=True,
+                encoding="utf-8",
+            ) as process:
+                output_lines: List[str] = []
+                for line in process.stdout:
                     sys.stdout.write(line)
                     output_lines.append(line)
 
-                process.stdout.close()
                 return_code = process.wait()
                 captured_output = "".join(output_lines)
 
                 if return_code:
-                    # Manually raise error with the combined output
                     raise subprocess.CalledProcessError(
                         return_code, command, output=captured_output
                     )
                 return captured_output
-            else:
-                result = subprocess.run(
-                    command,
-                    capture_output=True,
-                    text=True,
-                    check=True,
-                    encoding=locale.getpreferredencoding(False),
-                )
-                return result.stdout
 
     except FileNotFoundError:
         print(
@@ -125,13 +169,84 @@ def run(
         )
         raise
 
-    except subprocess.CalledProcessError as e:
+    except subprocess.CalledProcessError as error:
         print("Error running opendataloader-pdf CLI.", file=sys.stderr)
-        print(f"Return code: {e.returncode}", file=sys.stderr)
-        if e.output:
-            print(f"Output: {e.output}", file=sys.stderr)
-        elif e.stderr:
-            print(f"Stderr: {e.stderr}", file=sys.stderr)
-        if e.stdout:
-            print(f"Stdout: {e.stdout}", file=sys.stderr)
-        raise e
+        print(f"Return code: {error.returncode}", file=sys.stderr)
+        if error.output:
+            print(f"Output: {error.output}", file=sys.stderr)
+        if error.stderr:
+            print(f"Stderr: {error.stderr}", file=sys.stderr)
+        if error.stdout:
+            print(f"Stdout: {error.stdout}", file=sys.stderr)
+        raise
+
+
+def main(argv=None) -> int:
+    """CLI entry point for running the wrapper from the command line."""
+    parser = argparse.ArgumentParser(
+        description="Run the opendataloader-pdf CLI using the bundled JAR."
+    )
+    parser.add_argument(
+        "input_path", nargs="+", help="Path to the input PDF file or directory."
+    )
+    parser.add_argument(
+        "-o",
+        "--output-dir",
+        help="Directory where outputs are written.",
+    )
+    parser.add_argument("-p", "--password", help="Password for encrypted PDFs.")
+    parser.add_argument(
+        "-f",
+        "--format",
+        nargs="+",
+        choices=[
+            "json",
+            "text",
+            "html",
+            "pdf",
+            "markdown",
+            "markdown-with-html",
+            "markdown-with-images",
+        ],
+        help="Output format(s) to generate.",
+    )
+    parser.add_argument(
+        "-q",
+        "--quiet",
+        action="store_true",
+        help="Suppress CLI logging output.",
+    )
+    parser.add_argument(
+        "--content-safety-off",
+        nargs="+",
+        choices=[
+            "all",
+            "hidden-text",
+            "off-page",
+            "tiny",
+            "hidden-ocg",
+        ],
+        help="Disables one or more content safety filters. Accepts a list of filter names.",
+    )
+    parser.add_argument(
+        "--keep-line-breaks",
+        action="store_true",
+        help="Preserve line breaks in text output.",
+    )
+    parser.add_argument(
+        "--replace-invalid-chars",
+        help="Replacement character for invalid or unrecognized characters.",
+    )
+    args = parser.parse_args(argv)
+
+    try:
+        convert(**vars(args))
+    except FileNotFoundError as err:
+        print(err, file=sys.stderr)
+        return 1
+    except subprocess.CalledProcessError as err:
+        return err.returncode or 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

{opendataloader_pdf-1.0.5.dist-info → opendataloader_pdf-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opendataloader-pdf
-Version: 1.0.5
+Version: 1.1.0
 Summary: A Python wrapper for the opendataloader-pdf Java CLI.
 Home-page: https://github.com/opendataloader-project/opendataloader-pdf
 Author: opendataloader-project
@@ -97,40 +97,42 @@ pip install -U opendataloader-pdf
 
 ### Usage
 
-- input_path can be either the path to a single document or the path to a folder.
-- If you don’t specify an output_folder, the output data will be saved in the same directory as the input document.
+input_path can be either the path to a single document or the path to a folder.
 
 ```python
 import opendataloader_pdf
 
-opendataloader_pdf.run(
-    input_path="path/to/document.pdf",
-    output_folder="path/to/output",
-    generate_markdown=True,
-    generate_html=True,
-    generate_annotated_pdf=True,
+opendataloader_pdf.convert(
+    input_path=["path/to/document.pdf", "path/to/folder"],
+    output_dir="path/to/output",
+    format=["json", "html", "pdf", "markdown"]
 )
 ```
 
-### Function: run()
+If you want to run it via CLI, you can use the following command on the terminal:
+
+```bash
+opendataloader-pdf path/to/document.pdf path/to/folder -o path/to/output -f json html pdf markdown
+```
+
+### Function: convert()
 
 The main function to process PDFs.
 
-| Parameter                | Type   | Required | Default      | Description                                                                                                                                 |
-|--------------------------| ------ | -------- |--------------|---------------------------------------------------------------------------------------------------------------------------------------------|
-| `input_path`             | `str`  | ✅ Yes    | —            | Path to the input PDF file or folder.                                                                                                       |
-| `output_folder`          | `str`  | No       | input folder | Path to the output folder.                                                                                                                  |
-| `password`               | `str`  | No       | `None`       | Password for the PDF file.                                                                                                                  |
-| `replace_invalid_chars`  | `str`  | No       | `" "`       | Character to replace invalid or unrecognized characters (e.g., �, \u0000)                                                                   |
-| `content_safety_off`     | `str`  | No       | `None`       | Disables one or more content safety filters. Accepts a comma-separated list of filter names. Arguments: all, hidden-text, off-page, tiny, hidden-ocg. |
-| `generate_markdown`      | `bool` | No       | `False`      | If `True`, generates a Markdown output file.                                                                                                |
-| `generate_html`          | `bool` | No       | `False`      | If `True`, generates an HTML output file.                                                                                                   |
-| `generate_annotated_pdf` | `bool` | No       | `False`      | If `True`, generates an annotated PDF output file.                                                                                          |
-| `keep_line_breaks`       | `bool` | No       | `False`      | If `True`, keeps line breaks in the output.                                                                                                 |
-| `html_in_markdown`       | `bool` | No       | `False`      | If `True`, uses HTML in the Markdown output.                                                                                                |
-| `add_image_to_markdown`  | `bool` | No       | `False`      | If `True`, adds images to the Markdown output.                                                                                              |
-| `no_json`                | `bool` | No       | `False`      | If `True`, disables the JSON output.                                                                                                        |
-| `debug`                  | `bool` | No       | `False`      | If `True`, prints CLI messages to the console during execution.                                                                             |
+| Parameter                | Type           | Required | Default      | Description                                                                                                                                 |
+|--------------------------|----------------| -------- |--------------|---------------------------------------------------------------------------------------------------------------------------------------------|
+| `input_path`             | `List[str]`     | ✅ Yes    | —            | One or more PDF file paths or directories to process.                                                                                       |
+| `output_dir`             | `Optional[str]` | No       | input folder | Directory where outputs are written.                                                                                                       |
+| `password`               | `Optional[str]` | No       | `None`       | Password used for encrypted PDFs.                                                                                                           |
+| `format`                 | `Optional[List[str]]` | No | `None`       | Output formats to generate (e.g. `"json"`, `"html"`, `"pdf"`, `"text"`, `"markdown"`, `"markdown-with-html"`, `"markdown-with-images"`).                                                             |
+| `quiet`                  | `bool`          | No       | `False`      | Suppresses CLI logging output when `True`.                                                                                                  |
+| `content_safety_off`     | `Optional[List[str]]` | No | `None`       | List of content safety filters to disable (e.g. `"all"`, `"hidden-text"`, `"off-page"`, `"tiny"`, `"hidden-ocg"`).                      |
+| `keep_line_breaks`       | `bool`          | No       | `False`      | Preserves line breaks in text output when `True`.                                                                                           |
+| `replace_invalid_chars`  | `Optional[str]` | No       | `None`       | Replacement character for invalid or unrecognized characters (e.g., �, `\u0000`).                                                           |
+
+### Function: run()
+
+Deprecated.
 
 <br/>
 
@@ -174,6 +176,24 @@ async function main() {
 main();
 ```
 
+If you want to run it via CLI, you can use the following command:
+
+```bash
+npx @opendataloader/pdf path/to/document.pdf -o path/to/output --markdown --html --pdf
+```
+
+or you can install it globally:
+
+```bash
+npm install -g @opendataloader/pdf
+```
+
+then run:
+
+```bash
+opendataloader-pdf path/to/document.pdf -o path/to/output --markdown --html --pdf
+```
+
 ### Function: run()
 
 `run(inputPath: string, options?: RunOptions): Promise<string>`
@@ -343,16 +363,23 @@ The images are extracted from PDF as individual files and stored in a subfolder
 ```
 Options:
 -o,--output-dir <arg>           Specifies the output directory for generated files
+-p,--password <arg>             Specifies the password for an encrypted PDF
+-f,--format <arg>               List of output formats to generate (json, text, html, pdf, markdown, markdown-with-html, markdown-with-images). Default: json
+-q,--quiet                      Suppresses console logging output
+--content-safety-off <arg>      Disables one or more content safety filters. Accepts a list of filter names. Arguments: all, hidden-text, off-page, tiny, hidden-ocg
 --keep-line-breaks              Preserves original line breaks in the extracted text
---content-safety-off <arg>      Disables one or more content safety filters. Accepts a comma-separated list of filter names. Arguments: all, hidden-text, off-page, tiny, hidden-ocg
---markdown-with-html            Sets the data extraction output format to Markdown with rendering complex elements like tables as HTML for better structure
---markdown-with-images          Sets the data extraction output format to Markdown with extracting images from the PDF and includes them as links
---markdown                      Sets the data extraction output format to Markdown
---html                          Sets the data extraction output format to HTML
+--replace-invalid-chars <arg>   Replaces invalid or unrecognized characters (e.g., �, \u0000) with the specified character
+```
+
+The legacy options (for backward compatibility):
+
+```
 --no-json                       Disables the JSON output format
--p,--password <arg>             Specifies the password for an encrypted PDF
+--html                          Sets the data extraction output format to HTML
 --pdf                           Generates a new PDF file where the extracted layout data is visualized as annotations
---replace-invalid-chars <arg>   Replaces invalid or unrecognized characters (e.g., �, \u0000) with the specified character
+--markdown                      Sets the data extraction output format to Markdown
+--markdown-with-html            Sets the data extraction output format to Markdown with rendering complex elements like tables as HTML for better structure
+--markdown-with-images          Sets the data extraction output format to Markdown with extracting images from the PDF and includes them as links
 ```
 
 ### Schema of the JSON output

{opendataloader_pdf-1.0.5.dist-info → opendataloader_pdf-1.1.0.dist-info}/RECORD

@@ -1,7 +1,8 @@
 opendataloader_pdf/LICENSE,sha256=rxdbnZbuk8IaA2FS4bkFsLlTBNSujCySHHYJEAuo334,15921
 opendataloader_pdf/NOTICE.md,sha256=Uxc6sEbVz2hfsDinzzSNMtmsjx9HsQUod0yy0cswUwg,562
-opendataloader_pdf/__init__.py,sha256=T5RV-dcgjNCm8klNy_EH-IgOeodcPg6Yc34HHXtuAmQ,44
-opendataloader_pdf/wrapper.py,sha256=WL7qTsX214L0jXxlSDesYadRVpdrsLQd2Hgum5BdD1s,4962
+opendataloader_pdf/__init__.py,sha256=xkTyVWNu1W2YrI1tPpGnd11DwwcwFDyBp8b4agLdd7A,64
+opendataloader_pdf/__main__.py,sha256=lmla4yz3SaYBfRJXOXnwO_8ID31-Ja20aQmomiz1eEc,84
+opendataloader_pdf/wrapper.py,sha256=0Erld0Cpu5rXhT46WpqNkrg0bBg15iBmaH-AU9CfdNU,8409
 opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_LICENSES.md,sha256=QRYYiXFS2zBDGdmWRo_SrRfGhrdRBwhiRo1SdUKfrQo,11235
 opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_NOTICES.md,sha256=pB2ZitFM1u0x3rIDpMHsLxOe4OFNCZRqkzeR-bfpFzE,8911
 opendataloader_pdf/THIRD_PARTY/licenses/Apache-2.0.txt,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
@@ -13,8 +14,9 @@ opendataloader_pdf/THIRD_PARTY/licenses/LICENSE-JJ2000.txt,sha256=itSesIy3XiNWgJ
 opendataloader_pdf/THIRD_PARTY/licenses/MIT.txt,sha256=JPCdbR3BU0uO_KypOd3sGWnKwlVHGq4l0pmrjoGtop8,1078
 opendataloader_pdf/THIRD_PARTY/licenses/MPL-2.0.txt,sha256=CGF6Fx5WV7DJmRZJ8_6w6JEt2N9bu4p6zDo18fTHHRw,15818
 opendataloader_pdf/THIRD_PARTY/licenses/Plexus Classworlds License.txt,sha256=ZQuKXwVz4FeC34ApB20vYg8kPTwgIUKRzEk5ew74-hU,1937
-opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=Z9WU68Tw5ckOTgnlUPJs_Jub_C6ZGyQ-0sqjjSNMYYk,20477542
-opendataloader_pdf-1.0.5.dist-info/METADATA,sha256=RNIDw03Rwl4wGRSPIhbHR6VyTzhc7cnlYHEEIajZBTk,25452
-opendataloader_pdf-1.0.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-opendataloader_pdf-1.0.5.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
-opendataloader_pdf-1.0.5.dist-info/RECORD,,
+opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=0mrZFl8pVTrUIf8Nk09wN9KJPWW1U8ZMvdyB9sEPt-c,20485612
+opendataloader_pdf-1.1.0.dist-info/METADATA,sha256=jk-YV7lX5a9wqL57cLhAhJr_bgXEOBSY2RGL67lDN34,25270
+opendataloader_pdf-1.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+opendataloader_pdf-1.1.0.dist-info/entry_points.txt,sha256=Tupa9pVNF6nXD9sqzCLI8PCHbSu0jKkL3SYyTkQy0dc,71
+opendataloader_pdf-1.1.0.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
+opendataloader_pdf-1.1.0.dist-info/RECORD,,

opendataloader_pdf-1.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+opendataloader-pdf = opendataloader_pdf.wrapper:main