Redesigned test cases for Issue damies13#37 and Issue damies13#38 to …

…make them more readable and resistant to changes.

They are now written in the same style as Issue damies13#36 Test Case.

Tests/Regression/Reporter/read_docx.py

@@ -3,6 +3,7 @@
 import subprocess
 
 from docx import Document
+import docx
 from docx.oxml.shared import OxmlElement, qn
 
 
@@ -22,7 +23,7 @@ def read_paragraphs_docx_file(docx_path: str) -> dict:
             if current_heading:
                 doc_sections[current_heading].append(paragraph.text.strip())
             else:
-                doc_sections.setdefault('No Heading', []).append(paragraph.text.strip())
+                doc_sections.setdefault('Cover', []).append(paragraph.text.strip())
 
     return doc_sections
 
@@ -53,6 +54,73 @@ def update_table_of_contents(docx_path: str):
     doc.save(docx_path)
 
 
+def extract_docx_images_under_heading(heading:str, docx_path:str, output_folder:str, debug=False) -> list:
+    """
+    Extract images from a DOCX file, including images inside tables,
+    and associate them to the provided heading.
+    """
+    doc = Document(docx_path)
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+
+    image_counter = 1
+    current_heading_name = None
+    image_list = []
+
+    def extract_images_from_run(run, heading, output_folder):
+        """Extract images from a run and save them to the given output folder."""
+        nonlocal image_counter
+
+        if run.element.xpath('.//w:drawing'):
+            for rel in run.element.xpath('.//a:blip/@r:embed'):
+                part = doc.part.related_parts[rel]
+
+                image_name = f"{heading.replace(" ", "_")}_{image_counter}_image.png"
+                image_path = os.path.join(output_folder, image_name)
+
+                with open(image_path, 'wb') as img_file:
+                    img_file.write(part.blob)
+
+                print(f"DOCX RFSwarm report image saved as: {image_name}") if debug else 0
+                image_list.append(image_name)
+                image_counter += 1
+
+    for inner_obj in doc.iter_inner_content():
+        image_counter = 1
+
+        if isinstance(inner_obj, docx.text.paragraph.Paragraph):
+            paragraph = inner_obj
+            if paragraph.style.name.startswith("Heading"):
+                heading_name = paragraph.text.strip()
+                heading_name_splitted = heading_name.split(" ", maxsplit=1)
+                current_heading_name = heading_name_splitted[1]
+
+            if current_heading_name == heading:
+                for run in paragraph.runs:
+                    extract_images_from_run(run, current_heading_name, output_folder)
+
+        elif isinstance(inner_obj, docx.table.Table):
+            if current_heading_name == heading:
+                table = inner_obj
+                def iter_unique_row_cells(row):
+                    """Generate cells in given row skipping empty grid cells."""
+                    last_cell_tc = None
+                    for cell in row.cells:
+                        this_cell_tc = cell._tc
+                        if this_cell_tc is last_cell_tc:
+                            continue
+                        last_cell_tc = this_cell_tc
+                        yield cell
+
+                for row in table.rows:
+                    for cell in iter_unique_row_cells(row):
+                        for paragraph in cell.paragraphs:
+                            for run in paragraph.runs:
+                                extract_images_from_run(run, current_heading_name, output_folder)
+
+    return image_list
+
+
 def extract_images_from_docx(docx_path: str, output_folder: str) -> list:
     """
     Extract all images from DOCX one by one.
@@ -71,20 +139,16 @@ def extract_images_from_docx(docx_path: str, output_folder: str) -> list:
 
             with open(os.path.join(output_folder, img_name), "wb") as img_file:
                 img_file.write(img_data)
-                print(f"DOCX RFSwarm raport image saved as: {img_name}")
+                print(f"DOCX RFSwarm report image saved as: {img_name}")
                 saved_images.append(img_name)
 
     return saved_images
 
 
-def extract_tables_from_docx(docx_path: str) -> list:
+def extract_table_from_docx(docx_table_obj: docx.table.Table) -> list:
     """
-    Extract all tables from DOCX one by one.
-    Returns nested lists of tables.
-    Note: For RFSwarm DOCX raport the first value of each row will be empty.
+    Extract table from docx.table.Table object as nested list.
     """
-    doc = Document(docx_path)
-    tables = []
 
     def iter_unique_row_cells(row):
         """Generate cells in given row skipping empty grid cells."""
@@ -96,16 +160,14 @@ def iter_unique_row_cells(row):
             last_cell_tc = this_cell_tc
             yield cell
 
-    for table in doc.tables:
-        table_data = []
-        for row in table.rows:
-            row_data = []
-            for cell in iter_unique_row_cells(row):
-                row_data.append(cell.text)
-            table_data.append(row_data)
-        tables.append(table_data)
+    table_data = []
+    for row in docx_table_obj.rows:
+        row_data = []
+        for cell in iter_unique_row_cells(row):
+            row_data.append(cell.text)
+        table_data.append(row_data)
 
-    return tables
+    return table_data
 
 
 def sort_docx_images(docx_images: list) -> list:
@@ -114,3 +176,45 @@ def natural_sort_key(filename):
         return [int(text) if text.isdigit() else text for text in re.split(r'(\d+)', filename)]
 
     return sorted(docx_images, key=natural_sort_key)
+
+
+def read_docx_file(docx_path: str, debug=False) -> dict:
+    """
+    Read the docx file in terms of text and table content.
+    Saved data is saved as:
+    dict = {"Heading 1" = {"text" = ["line 1", "line 2", ...], "table" = [[row 1], [row 2], ...] }, ...}
+    """
+    doc = Document(docx_path)
+    doc_data = dict()
+
+    current_heading_name = None
+
+    for inner_obj in doc.iter_inner_content():
+        if isinstance(inner_obj, docx.text.paragraph.Paragraph):
+            paragraph = inner_obj
+            if paragraph.style.name.startswith('Heading'):
+                heading_name = paragraph.text.strip()
+                heading_name_splitted = heading_name.split(" ", maxsplit=1)
+                current_heading_name = heading_name_splitted[1]
+                doc_data.setdefault(current_heading_name, {"text":[], "table":[]})
+
+            elif paragraph.text.strip():
+                if current_heading_name:
+                    print(paragraph.text.strip())
+                    doc_data[current_heading_name]["text"].append(paragraph.text.strip())
+                else:
+                    print(paragraph.text.strip())
+                    doc_data.setdefault("Cover", {"text":[]})
+                    doc_data["Cover"]["text"].append(paragraph.text.strip())
+
+        elif isinstance(inner_obj, docx.table.Table):
+            table = inner_obj
+            table_list = extract_table_from_docx(table)
+            doc_data[current_heading_name]["table"] = table_list
+
+    if debug:
+        for k in doc_data:
+            print(" -",k,":")
+            print(doc_data[k], end="\n\n\n")
+
+    return doc_data

Tests/Regression/Reporter/read_xlsx.py

@@ -24,11 +24,28 @@ def read_all_xlsx_text_data(xlsx_path: str) -> list:
     return xlsx_tables
 
 
-def read_xlsx_text_data_from_sheet(xlsx_path: str, sheet_name: str) -> list:
+def get_xlsx_sheet_by_name(xlsx_path: str, sheet_name: str) -> list:
     """
-    Read xlsx text data from given xlsx sheet.
+    Find the full name of the xlsx sheet by its name.
+    For example: given: "Contents tables" output: "4 Contents tables".
     """
-    all_excel_data_frame = read_excel(xlsx_path, sheet_name, keep_default_na=False, na_values=['NaN'])
+    xlsx_sheets = load_workbook(xlsx_path, keep_links=False).sheetnames
+    for sheet in xlsx_sheets:
+        if " " in list(sheet):
+            sheet_fragmented = sheet.split(" ", maxsplit=1)
+            if sheet_fragmented[1] == sheet_name:
+                return sheet
+
+    return 0
+
+
+def read_xlsx_text_data_from_sheet(xlsx_path: str, sheet: str, start_at=None, stop_at=None) -> list:
+    """
+    Read xlsx text data from the given xlsx sheet.
+    start_at - start from the specified string, but do not include it.
+    stop_at - end at specified string, and don't include it.
+    """
+    all_excel_data_frame = read_excel(xlsx_path, sheet, keep_default_na=False, na_values=['NaN'])
     excel_data_list = all_excel_data_frame.values.tolist()
 
     for row_n in range(len(excel_data_list) - 1, -1, -1):
@@ -39,18 +56,29 @@ def read_xlsx_text_data_from_sheet(xlsx_path: str, sheet_name: str) -> list:
         if len(excel_data_list[row_n]) == 0:
             excel_data_list.pop(row_n)
 
-    return excel_data_list
+    start_index = 0
+    end_index = len(excel_data_list)
+    if start_at is not None:
+        for row_n in range(0, len(excel_data_list)):
+            if start_at in excel_data_list[row_n]:
+                start_index = row_n + 1
+    if stop_at is not None:
+        for row_n in range(0, len(excel_data_list)):
+            if stop_at in excel_data_list[row_n]:
+                end_index = row_n
+
+    return excel_data_list[start_index : end_index]
 
 
-def extract_image_from_xlsx_sheet(xlsx_path: str, xlsx_sheet: str, cell_id: str, output_folder: str, show_image: bool = False):
+def extract_image_from_xlsx_sheet(xlsx_path: str, sheet: str, cell_id: str, output_folder: str, show_image: bool = False):
     """
     Extract an image from XLSX file from a given cell in specified sheet.
     Returns name of the saved image.
     """
     wb = load_workbook(xlsx_path, keep_links=False)
-    sheet = wb[xlsx_sheet]
+    sheet_obj = wb[sheet]
     try:
-        image_loader = SheetImageLoader(sheet)
+        image_loader = SheetImageLoader(sheet_obj)
     except Exception as e:
         raise AssertionError("Error in SheetImageLoader:", e)
     try:
@@ -60,7 +88,7 @@ def extract_image_from_xlsx_sheet(xlsx_path: str, xlsx_sheet: str, cell_id: str,
         return 0
     if show_image:
         image.show()
-    img_name = (xlsx_sheet + "_" + cell_id + "_image.png").replace(" ", "_")
+    img_name = (sheet + "_" + cell_id + "_image.png").replace(" ", "_")
 
     if not os.path.exists(output_folder):
         os.makedirs(output_folder)

Tests/Regression/Reporter/report_expected_data.yaml

@@ -1,3 +1,6 @@
+Cover:
+  text: ['quickdemo', '2023-07-28 07:42 - 07:50']
+
 Contents contents:
   text: ['This is Heading', 'Contents contents', 'Contents graphs', 'Contents tables', 'Note', 'Second Note', 'Third Note',
   'Data Graph Left Metric', 'Data Graph Left Result', 'Data Graph Left Result FAIL', 'Data Graph Left Result TPS',
@@ -17,6 +20,9 @@ Contents tables:
 Note:
   text: ['Hello i am a simple and obvious note :-)', 'This is just second line.', ' - first line', ' - second line', ' - third line', ""]
 
+Note DOCX:
+  text: ['Hello i am a simple and obvious note :-)', 'This is just second line.', '- first line', '- second line', '- third line']
+
 Second Note:
   text: ['This is my second note.']
 
@@ -73,6 +79,26 @@ Data Table ResultSummary:
   mid_row: ['_', 'Odoo Open Receipt', 'None', 'None', 'None', 'None', 'None', '0', '0', '1']
   upper_mid_row: ['_', 'Returns the number of elements matching ``locator``.', '0.012', '0.012', 'None', '0.012', 'None', '1', '0', '2']
 
+Data Table ResultSummary XLSX: # special version for XLSX
+  length: 42
+  header: ['Result Name', 'Minimum', 'Average', '90%ile', 'Maximum', 'Std. Dev.', 'Pass', 'Fail', 'Other']
+  rows_numbers: [1, -1, 11, 21, 31]
+  first_row: [':example: ''John Doe''', '0.001', '0.001', 'None', '0.001', '0.0', '4', '0', '0']
+  last_row: ['Waits until the element ``locator`` is visible.', '0.045', '0.115', 'None', '0.204', '0.078', '5', '0', '0']
+  quater_row: ['Odoo Confirm RFQ', 'None', 'None', 'None', 'None', 'None', '0', '1', '1']
+  mid_row: ['Odoo Open Receipt', 'None', 'None', 'None', 'None', 'None', '0', '0', '1']
+  upper_mid_row: ['Returns the number of elements matching ``locator``.', '0.012', '0.012', 'None', '0.012', 'None', '1', '0', '2']
+
+Data Table ResultSummary DOCX: # special version for DOCX
+  length: 42
+  header: ["", 'Result Name', 'Minimum', 'Average', '90%ile', 'Maximum', 'Std. Dev.', 'Pass', 'Fail', 'Other']
+  rows_numbers: [1, -1, 11, 21, 31]
+  first_row: ["", ':example: ''John Doe''', '0.001', '0.001', 'None', '0.001', '0.0', '4', '0', '0']
+  last_row: ["", 'Waits until the element ``locator`` is visible.', '0.045', '0.115', 'None', '0.204', '0.078', '5', '0', '0']
+  quater_row: ["", 'Odoo Confirm RFQ', 'None', 'None', 'None', 'None', 'None', '0', '1', '1']
+  mid_row: ["", 'Odoo Open Receipt', 'None', 'None', 'None', 'None', 'None', '0', '0', '1']
+  upper_mid_row: ["", 'Returns the number of elements matching ``locator``.', '0.012', '0.012', 'None', '0.012', 'None', '1', '0', '2']
+
 Data Table Polish Lang:
   length: 42
   header: ['Nazwa Wyniku', 'Minimum', 'Średnia', '90%yl', 'Maksimum', 'Odchylenie Standardowe', 'Pomyślnie', 'Niepowodzenie', 'Inne']