opendataloader-pdf 1.0.3__py3-none-any.whl → 1.0.5__py3-none-any.whl

opendataloader_pdf/wrapper.py

@@ -3,24 +3,11 @@ import sys
 import importlib.resources as importlib_resources
 import locale
 from pathlib import Path
-from typing import List
 
 # The consistent name of the JAR file bundled with the package
 _JAR_NAME = "opendataloader-pdf-cli.jar"
 
 
-def _get_redacted_command_string(command: List[str]) -> str:
-    """Redacts the password from a command list for safe logging."""
-    command_for_logging = list(command)
-    try:
-        password_index = command_for_logging.index("--password")
-        if password_index + 1 < len(command_for_logging):
-            command_for_logging[password_index + 1] = "[REDACTED]"
-    except ValueError:
-        pass  # '--password' not in command
-    return " ".join(command_for_logging)
-
-
 def run(
     input_path: str,
     output_folder: str = None,
@@ -33,6 +20,7 @@ def run(
     content_safety_off: str = None,
     html_in_markdown: bool = False,
     add_image_to_markdown: bool = False,
+    no_json: bool = False,
     debug: bool = False,
 ):
     """
@@ -49,6 +37,7 @@ def run(
         keep_line_breaks: If True, keeps line breaks in the output.
         html_in_markdown: If True, uses HTML in the Markdown output.
         add_image_to_markdown: If True, adds images to the Markdown output.
+        no_json: If True, disable the JSON output.
         debug: If True, prints all messages from the CLI to the console during execution.
 
     Returns:
@@ -68,6 +57,8 @@ def run(
         args.extend(["--password", password])
     if replace_invalid_chars:
         args.extend(["--replace-invalid-chars", replace_invalid_chars])
+    if content_safety_off:
+        args.extend(["--content-safety-off", content_safety_off])
     if generate_markdown:
         args.append("--markdown")
     if generate_html:
@@ -76,12 +67,12 @@ def run(
         args.append("--pdf")
     if keep_line_breaks:
         args.append("--keep-line-breaks")
-    if content_safety_off:
-        args.append(["--content-safety-off", content_safety_off])
     if html_in_markdown:
         args.append("--markdown-with-html")
     if add_image_to_markdown:
         args.append("--markdown-with-images")
+    if no_json:
+        args.append("--no-json")
 
     args.append(input_path)
 
@@ -94,7 +85,6 @@ def run(
             command = ["java", "-jar", str(jar_path)] + args
 
             if debug:
-                print(f"Running command: {_get_redacted_command_string(command)}", file=sys.stderr)
                 process = subprocess.Popen(
                     command,
                     stdout=subprocess.PIPE,
@@ -144,4 +134,4 @@ def run(
             print(f"Stderr: {e.stderr}", file=sys.stderr)
         if e.stdout:
             print(f"Stdout: {e.stdout}", file=sys.stderr)
-        raise e
+        raise e

{opendataloader_pdf-1.0.3.dist-info → opendataloader_pdf-1.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opendataloader-pdf
-Version: 1.0.3
+Version: 1.0.5
 Summary: A Python wrapper for the opendataloader-pdf Java CLI.
 Home-page: https://github.com/opendataloader-project/opendataloader-pdf
 Author: opendataloader-project
@@ -62,13 +62,24 @@ AI-safety is enabled by default and automatically filters likely prompt-injectio
 
 ## 🚀 Upcoming Features
 
-- 🖨️ **OCR for scanned PDFs** — Extract data from image-only pages
-- 🧠 **Table AI option** — Higher accuracy for tables with borderless or merged cells
-- ⚡ **Performance Benchmarks** — Transparent evaluations with open datasets and metrics, reported regularly
-- 🛡️ **AI Red Teaming** — Transparent adversarial benchmarks with datasets and metrics, reported regularly
+**Scheduled for November**
+- 📄 **Tagged PDF** — Develop advanced data extraction technology based on Tagged PDF
+- ⚡ **Performance Improvement** — Enhance the inference skill for greater accuracy and speed. 
+- 📊 **Benchmarks & Datasets** — Publish transparent evaluations using open datasets and standardized metrics. 
+- 🎯 **Metrics** — Publish the calculation methods to transparently share benchmark results.
 
 <br/>
 
+**Scheduled for December**
+- 🖨️ **OCR for scanned PDFs** — Extract data from image-only pages. 
+- 🧠 **Table AI option** — Higher accuracy for tables with borderless or merged cells. 
+<br/>
+
+**Scheduled for 2026**
+- 🛡️ **AI Red Teaming** — Transparent adversarial benchmarks with datasets and metrics, then reported regularly.
+  
+<br/>
+
 ## Prerequisites
 
 - Java 11 or higher must be installed and available in your system's PATH.
@@ -118,6 +129,7 @@ The main function to process PDFs.
 | `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.                                                                             |
 
 <br/>
@@ -189,6 +201,7 @@ The main function to process PDFs.
 | `keepLineBreaks`        | `boolean` | `false`       | If `true`, keeps line breaks in the output.                                                                                                           |
 | `htmlInMarkdown`        | `boolean` | `false`       | If `true`, uses HTML in the Markdown output.                                                                                                          |
 | `addImageToMarkdown`    | `boolean` | `false`       | If `true`, adds images to the Markdown output.                                                                                                        |
+| `noJson`                | `boolean` | `false`       | If `true`, disables the JSON output.                                                                                                                  |
 | `debug`                 | `boolean` | `false`       | If `true`, prints CLI messages to the console during execution.                                                                                       |
 
 <br/>
@@ -336,6 +349,7 @@ Options:
 --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
+--no-json                       Disables the JSON output format
 -p,--password <arg>             Specifies the password for an encrypted PDF
 --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

{opendataloader_pdf-1.0.3.dist-info → opendataloader_pdf-1.0.5.dist-info}/RECORD

@@ -1,7 +1,7 @@
 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=723K0YL0P9JSD_2pQ0w8je3dINy5s8rvYoQhyi6Z8PY,5437
+opendataloader_pdf/wrapper.py,sha256=WL7qTsX214L0jXxlSDesYadRVpdrsLQd2Hgum5BdD1s,4962
 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 +13,8 @@ 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=Xj3vHN5EyNydUtNheaZT81gvATHhX_q1tYt9yRCt8EA,20472831
-opendataloader_pdf-1.0.3.dist-info/METADATA,sha256=1nB-I81XSIeqVrFdiODmdJyKRx0yfbyNLPO_jhqRz5Q,24580
-opendataloader_pdf-1.0.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-opendataloader_pdf-1.0.3.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
-opendataloader_pdf-1.0.3.dist-info/RECORD,,
+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,,