sparrow-parse 0.2.0__tar.gz → 0.2.2__tar.gz

{sparrow_parse-0.2.0 → sparrow_parse-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.2.0
+Version: 0.2.2
 Summary: Sparrow Parse is a Python package for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 License: GPL-3.0

{sparrow_parse-0.2.0 → sparrow_parse-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sparrow-parse"
-version = "0.2.0"
+version = "0.2.2"
 description = "Sparrow Parse is a Python package for parsing and extracting information from documents."
 authors = ["Andrej Baranovskij <andrejus.baranovskis@gmail.com>"]
 license = "GPL-3.0"

sparrow_parse-0.2.2/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.2.2'

{sparrow_parse-0.2.0 → sparrow_parse-0.2.2}/sparrow_parse/extractor/html_extractor.py

@@ -3,8 +3,8 @@ from sentence_transformers import SentenceTransformer, util
 from bs4 import BeautifulSoup
 import json
 from rich.progress import Progress, SpinnerColumn, TextColumn
-from extractor_helper import merge_html_table_headers
-from extractor_helper import clean_html_table_header_names
+from .extractor_helper import merge_html_table_headers
+from .extractor_helper import clean_html_table_header_names
 import re
 
 
@@ -221,7 +221,10 @@ class HTMLExtractor(object):
 
 
 if __name__ == "__main__":
-    # with open('../data/invoice_1_table.txt', 'r') as file:
+    # to run for debugging, navigate to sparrow_parse and run the following command:
+    # python -m extractor.html_extractor
+
+    # with open('data/invoice_1_table.txt', 'r') as file:
     #     file_content = file.read()
     #
     # file_content = file_content.strip()[1:-1].strip()

{sparrow_parse-0.2.0 → sparrow_parse-0.2.2}/sparrow_parse/extractor/unstructured_processor.py

@@ -98,7 +98,7 @@ class UnstructuredProcessor(object):
         if options is None:
             content = self.process_json_file(file_path)
 
-        if options and "tables" in options and "html" in options:
+        if options and "tables" in options and "unstructured" in options:
             content = self.process_json_file(file_path, "form")
 
             table_content = self.process_json_file(file_path, "table")

sparrow_parse-0.2.0/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.2.0'