load libreoffice writer eval -batch 2

desktop_env/evaluators/metrics/docs.py

@@ -56,15 +56,34 @@ def compare_docx_files(file1, file2):
     doc2_paragraphs = [p.text for p in doc2.paragraphs]
 
     if len(doc1_paragraphs) != len(doc2_paragraphs):
+        # print(len(doc1_paragraphs))
+        # print(len(doc2_paragraphs))
         return 0
 
     # Compare each paragraph
     for p1, p2 in zip(doc1_paragraphs, doc2_paragraphs):
         if p1 != p2:
+            # print(p1)
+            # print(p2)
             return 0
 
     return 1
 
+def compare_init_lines(file1, file2):
+    doc1 = Document(file1)
+    doc2 = Document(file2)
+
+    doc1_paragraphs = [p.text for p in doc1.paragraphs]
+    doc2_paragraphs = [p.text for p in doc2.paragraphs]
+
+    # Compare each paragraph
+    for p1, p2 in zip(doc1_paragraphs, doc2_paragraphs):
+        if p1 != p2:
+            # print(p1)
+            # print(p2)
+            return 0
+
+    return 1
 
 def compare_docx_tables(docx_file1, docx_file2):
     doc1 = Document(docx_file1)
@@ -93,6 +112,8 @@ def compare_docx_tables(docx_file1, docx_file2):
 
 
 def compare_line_spacing(docx_file1, docx_file2):
+    if not compare_docx_files(docx_file1, docx_file2):
+        return 0
     doc1 = Document(docx_file1)
     doc2 = Document(docx_file2)
 
@@ -200,8 +221,10 @@ def compare_contains_image(docx_file1, docx_file2):
 # print(find_default_font("Ani", config_path))
 
 
-def evaluate_colored_words_in_tables(file_path):
-    document = Document(file_path)
+def evaluate_colored_words_in_tables(file_path1, file_path2):
+    if not compare_docx_files(file_path1, file_path2):
+        return 0
+    document = Document(file_path1)
 
     for table in document.tables:
         # Iterate through rows and cells in the table
@@ -221,8 +244,10 @@ def evaluate_colored_words_in_tables(file_path):
     return 1  # All words in tables are correctly colored
 
 
-def check_highlighted_words(file_path):
-    document = Document(file_path)
+def check_highlighted_words(file_path1, file_path2):
+    if not compare_docx_files(file_path1, file_path2):
+        return 0
+    document = Document(file_path1)
 
     for paragraph in document.paragraphs:
         for run in paragraph.runs:
@@ -232,8 +257,10 @@ def check_highlighted_words(file_path):
     return 1  # No highlighted words found
 
 
-def evaluate_strike_through_last_paragraph(file_path):
-    document = Document(file_path)
+def evaluate_strike_through_last_paragraph(file_path1, file_path2):
+    if not compare_docx_files(file_path1, file_path2):
+        return 0
+    document = Document(file_path1)
 
     # Get the last paragraph
     last_paragraph = document.paragraphs[-1]
@@ -278,8 +305,10 @@ def evaluate_spacing(file_path):
       return 0
 
 
-def check_italic_font_size_14(path):
-    document = Document(path)
+def check_italic_font_size_14(path1, path2):
+    if not compare_docx_files(path1, path2):
+        return 0
+    document = Document(path1)
     for paragraph in document.paragraphs:
         for run in paragraph.runs:
             if run.italic:
@@ -365,6 +394,8 @@ def compare_docx_lines(file1, file2):
 
     doc2 = Document(file2)
     doc2_lines = [p.text.strip() for p in doc2.paragraphs if p.text.strip()]
+    # print(doc1_lines)
+    # print(doc2_lines)
 
     # Convert the list of lines to sets and compare
     return set(doc1_lines) == set(doc2_lines)