Fixed duplicate results in table search

erikkastelec · Aug 26, 2020 · 1615719 · 1615719
1 parent fcc9260
commit 1615719
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 15 deletions.
diff --git a/PDFScraper/__init__.py b/PDFScraper/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "1.0.10"
+__version__ = "1.0.11"
 
 import argparse
 import logging

diff --git a/PDFScraper/outputGenerator.py b/PDFScraper/outputGenerator.py
@@ -300,20 +300,23 @@ def generate_html(output_path: str, docs: Documents, search_word: str, search_mo
                             tempfile_path = tempfile_path + "/table"
                             table.df[0].str.strip('.!? \n\t')
                             # perform fuzzy search over all columns
+                            found = False
                             for i in range(0, table.shape[1]):
-                                for x in process.extract(search_word, table.df[i].astype(str).values.tolist(),
-                                                         scorer=fuzz.partial_ratio):
-                                    if x[1] > 80:
-                                        table.to_html(tempfile_path, classes="responsive-table", index=False)
-                                        with codecs.open(tempfile_path, 'r') as table_file:
-                                            # replace \n in table to fix formatting
-                                            tab = re.sub(r'\\n', '<br>', table_file.read())
-                                            if not header_printed:
-                                                with tag('h2'):
-                                                    text("Found in document with location: " + str(document.path))
-                                            doc.asis(tab)
-                                            os.remove(tempfile_path)
-                                        break
+                                if not found:
+                                    for x in process.extract(search_word, table.df[i].astype(str).values.tolist(),
+                                                             scorer=fuzz.partial_ratio):
+                                        if x[1] > 80:
+                                            table.to_html(tempfile_path, classes="responsive-table", index=False)
+                                            with codecs.open(tempfile_path, 'r') as table_file:
+                                                # replace \n in table to fix formatting
+                                                tab = re.sub(r'\\n', '<br>', table_file.read())
+                                                if not header_printed:
+                                                    with tag('h2'):
+                                                        text("Found in document with location: " + str(document.path))
+                                                doc.asis(tab)
+                                                os.remove(tempfile_path)
+                                            found = True
+                                            break
 
     # write HTML to file
     # check if output path is a directory

diff --git a/setup.py b/setup.py
@@ -49,7 +49,7 @@
         "yattag==1.14.0",
     ],
     name="PDFScraper",
-    version="1.0.10",
+    version="1.0.11",
     author="Erik Kastelec",
     author_email="[email protected]",
     description="PDF text and table search",