sparrow-parse 0.2.5__tar.gz → 0.2.7__tar.gz

{sparrow_parse-0.2.5 → sparrow_parse-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.2.5
+Version: 0.2.7
 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-0.2.5 → sparrow_parse-0.2.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sparrow-parse"
-version = "0.2.5"
+version = "0.2.7"
 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-0.2.7/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.2.7'

{sparrow_parse-0.2.5 → sparrow_parse-0.2.7}/sparrow_parse/extractor/extractor_helper.py

@@ -273,6 +273,8 @@ def merge_rows_with_rowspan(html):
 
 
 def detect_and_remove_junk_columns(html_table, target_columns, debug=False):
+    html_table = clean_html_table_header_names(html_table)
+
     # Wrap the HTML string in a StringIO object
     html_buffer = StringIO(html_table)
 
@@ -356,6 +358,9 @@ def clean_html_table_header_names(html_table: str) -> str:
     headers = table.find_all("th")
     for th in headers:
         clean_header = re.sub(r"[^a-zA-Z0-9\s]", "", th.get_text())
+        # Check if the cleaned name is empty
+        if not clean_header.strip():
+            clean_header = "-"
         th.string.replace_with(clean_header)
 
     html_table = str(soup)

{sparrow_parse-0.2.5 → sparrow_parse-0.2.7}/sparrow_parse/extractor/html_extractor.py

@@ -24,7 +24,7 @@ class HTMLExtractor(object):
 
             json_result, targets_unprocessed = self.read_data_from_table(target_columns, table, column_keywords,
                                                                          group_by_rows, local, debug)
-            answer = self.add_answer_section(answer, "items" + str(i), json_result)
+            answer = self.add_answer_section(answer, "items" + str(i + 1), json_result)
 
             if update_targets:
                 target_columns = targets_unprocessed

sparrow_parse-0.2.5/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.2.5'