opendataloader-pdf 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

opendataloader_pdf/wrapper.py

@@ -1,13 +1,26 @@
 import subprocess
 import sys
-import importlib_resources
+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,
@@ -29,12 +42,11 @@ def run(
         input_path: Path to the input PDF file or folder.
         output_folder: Path to the output folder. Defaults to the input folder.
         password: Password for the PDF file.
-        replace_invalid_chars: Character to replace invalid or unrecognized characters (e.g., �, \u0000) with.
+        replace_invalid_chars: Character to replace invalid or unrecognized characters (e.g., , \u0000) with.
         generate_markdown: If True, generates a Markdown output file.
         generate_html: If True, generates an HTML output file.
         generate_annotated_pdf: If True, generates an annotated PDF output file.
         keep_line_breaks: If True, keeps line breaks in the output.
-        find_hidden_text: If True, finds hidden text in the PDF.
         html_in_markdown: If True, uses HTML in the Markdown output.
         add_image_to_markdown: If True, adds images to the Markdown output.
         debug: If True, prints all messages from the CLI to the console during execution.
@@ -82,7 +94,7 @@ def run(
             command = ["java", "-jar", str(jar_path)] + args
 
             if debug:
-                print(f"Running command: {' '.join(command)}", file=sys.stderr)
+                print(f"Running command: {_get_redacted_command_string(command)}", file=sys.stderr)
                 process = subprocess.Popen(
                     command,
                     stdout=subprocess.PIPE,
@@ -132,4 +144,4 @@ 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-1.0.0.dist-info → opendataloader_pdf-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opendataloader-pdf
-Version: 1.0.0
+Version: 1.0.1
 Summary: A Python wrapper for the opendataloader-pdf Java CLI.
 Home-page: https://github.com/opendataloader-project/opendataloader-pdf
 Author: opendataloader-project
@@ -8,9 +8,8 @@ Author-email: open.dataloader@hancom.com
 License: MPL-2.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.7
+Requires-Python: >=3.9, <4.0
 Description-Content-Type: text/markdown
-Requires-Dist: importlib_resources; python_version < "3.9"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -18,16 +17,15 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
-Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
 
 # OpenDataLoader PDF
 
-![Pre-release](https://img.shields.io/badge/Pre--release-FFA500&logo=github)
+
 [![License](https://img.shields.io/pypi/l/opendataloader-pdf.svg)](https://github.com/opendataloader-project/opendataloader-pdf/blob/main/LICENSE)
 ![Java](https://img.shields.io/badge/Java-11+-blue.svg)
-![Python](https://img.shields.io/badge/Python-3.8+-blue.svg)
+![Python](https://img.shields.io/badge/Python-3.9+-blue.svg)
 [![Maven Central](https://img.shields.io/maven-central/v/org.opendataloader/opendataloader-pdf-core.svg)](https://search.maven.org/artifact/org.opendataloader/opendataloader-pdf-core)
 [![PyPI version](https://img.shields.io/pypi/v/opendataloader-pdf.svg)](https://pypi.org/project/opendataloader-pdf/)
 [![npm version](https://img.shields.io/npm/v/@opendataloader/pdf.svg)](https://www.npmjs.com/package/@opendataloader/pdf)
@@ -74,7 +72,7 @@ AI-safety is enabled by default and automatically filters likely prompt-injectio
 ## Prerequisites
 
 - Java 11 or higher must be installed and available in your system's PATH.
-- Python 3.8+
+- Python 3.9+
 
 <br/>
 
@@ -213,7 +211,7 @@ Check for the latest version on [Maven Central](https://search.maven.org/artifac
         <dependency>
             <groupId>org.opendataloader</groupId>
             <artifactId>opendataloader-pdf-core</artifactId>
-            <version>0.0.16</version>
+            <version>1.0.0</version>
         </dependency>
     </dependencies>
 

{opendataloader_pdf-1.0.0.dist-info → opendataloader_pdf-1.0.1.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=bPy-wNmQfJpmCg9dVx9uNTrGfW446GdGNrlJnt0cosA,4960
+opendataloader_pdf/wrapper.py,sha256=723K0YL0P9JSD_2pQ0w8je3dINy5s8rvYoQhyi6Z8PY,5437
 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=YpRYRxfbUO2W_oPYigKziGqX1awk9xNWsGHfN_XS_tw,20470354
-opendataloader_pdf-1.0.0.dist-info/METADATA,sha256=IfUtznw8ufhoJXi1j38sbtYHZhIJebF_940cOhbsjqo,24527
-opendataloader_pdf-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-opendataloader_pdf-1.0.0.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
-opendataloader_pdf-1.0.0.dist-info/RECORD,,
+opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=pW9pLp40AhKPBn6UalczNCpzN2zesq0q7hhdl-hOSTw,20470360
+opendataloader_pdf-1.0.1.dist-info/METADATA,sha256=43ddIC8BVAzij8L3akH3MUq5Yd-C_80HVsVGb5cODz8,24374
+opendataloader_pdf-1.0.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+opendataloader_pdf-1.0.1.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
+opendataloader_pdf-1.0.1.dist-info/RECORD,,