sparrow-parse 0.2.8__tar.gz → 0.2.9__tar.gz

{sparrow_parse-0.2.8 → sparrow_parse-0.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.2.8
+Version: 0.2.9
 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-0.2.8 → sparrow_parse-0.2.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sparrow-parse"
-version = "0.2.8"
+version = "0.2.9"
 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-0.2.9/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.2.9'

{sparrow_parse-0.2.8 → sparrow_parse-0.2.9}/sparrow_parse/extractor/html_extractor.py

@@ -224,29 +224,29 @@ if __name__ == "__main__":
     # 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()
-    data_list = re.split(r"',\s*'", file_content)
-    data_list = [item.strip(" '") for item in data_list]
+    # with open('data/invoice_1_table.txt', 'r') as file:
+    #     file_content = file.read()
+    #
+    # file_content = file_content.strip()[1:-1].strip()
+    # data_list = re.split(r"',\s*'", file_content)
+    # data_list = [item.strip(" '") for item in data_list]
 
     extractor = HTMLExtractor()
 
-    answer, targets_unprocessed = extractor.read_data(
-        # ['description', 'qty', 'net_price', 'net_worth', 'vat', 'gross_worth'],
-        ['transaction_date', 'value_date', 'description', 'cheque', 'withdrawal', 'deposit', 'balance',
-         'deposits', 'account_number', 'od_limit', 'currency_balance', 'sgd_balance', 'maturity_date'],
-        data_list,
-        0.5,
-        0.3,
-        # None,
-        ['deposits', 'account_number', 'od_limit', 'currency_balance', 'sgd_balance', 'transaction_date',
-         'value_date', 'description', 'cheque', 'withdrawal', 'deposit', 'balance', 'maturity_date'],
-        True,
-        True,
-        True,
-        True)
-
-    print(answer)
-    print(targets_unprocessed)
+    # answer, targets_unprocessed = extractor.read_data(
+    #     # ['description', 'qty', 'net_price', 'net_worth', 'vat', 'gross_worth'],
+    #     ['transaction_date', 'value_date', 'description', 'cheque', 'withdrawal', 'deposit', 'balance',
+    #      'deposits', 'account_number', 'od_limit', 'currency_balance', 'sgd_balance', 'maturity_date'],
+    #     data_list,
+    #     0.5,
+    #     0.3,
+    #     # None,
+    #     ['deposits', 'account_number', 'od_limit', 'currency_balance', 'sgd_balance', 'transaction_date',
+    #      'value_date', 'description', 'cheque', 'withdrawal', 'deposit', 'balance', 'maturity_date'],
+    #     True,
+    #     True,
+    #     True,
+    #     True)
+    #
+    # print(answer)
+    # print(targets_unprocessed)

{sparrow_parse-0.2.8 → sparrow_parse-0.2.9}/sparrow_parse/extractor/unstructured_processor.py

@@ -177,11 +177,3 @@ if __name__ == "__main__":
     #     True,
     #     True)
 
-    content, table_content = processor.extract_data(
-        '/Users/andrejb/Documents/work/epik/bankstatement/OCBC_1_1.pdf',
-        'hi_res',
-        'yolox',
-        ['tables', 'unstructured'],
-        True,
-        True)
-

sparrow_parse-0.2.8/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.2.8'