Merge branch 'main' of https://github.com/ztjhz/DesktopEnv

desktop_env/evaluators/getters/__init__.py

@@ -7,3 +7,4 @@ from .misc import get_rule, get_accessibility_tree
 from .replay import get_replay
 from .vlc import get_vlc_playing_info, get_vlc_config
 from .vscode import get_vscode_config
+from .impress import get_audio_in_slide

desktop_env/evaluators/metrics/__init__.py

@@ -5,18 +5,18 @@ from .docs import find_default_font, contains_page_break, compare_docx_files, co
 from .docs import is_first_line_centered, check_file_exists, compare_contains_image
 from .docs import evaluate_colored_words_in_tables, check_highlighted_words, evaluate_strike_through_last_paragraph, \
     evaluate_conversion, evaluate_spacing, check_italic_font_size_14, evaluate_alignment, get_unique_train_ids, \
-    check_no_duplicates           
-from .general import exact_match, fuzzy_match, check_csv, check_accessibility_tree, check_list
+    check_no_duplicates
+from .general import exact_match, fuzzy_match
+from .general import check_csv, check_accessibility_tree, run_sqlite3, check_json
+from .gimp import increase_saturation, decrease_brightness, check_file_exists, compare_triangle_positions
+from .slides import check_presenter_console_disable, check_image_stretch_and_center, check_slide_numbers_color, compare_pptx_files, check_strikethrough, \
+    check_slide_orientation_Portrait, evaluate_presentation_fill_to_rgb_distance, check_left_panel
 from .libreoffice import check_libre_locale
 from .pdf import check_pdf_pages
 #from .table import check_sheet_list, check_xlsx_freeze, check_xlsx_zoom, check_data_validations
 from .table import compare_table
+from .thunderbird import check_thunderbird_prefs, check_thunderbird_filter
 from .vlc import is_vlc_playing, is_vlc_recordings_folder, is_vlc_fullscreen, compare_images, compare_audios, \
     compare_videos
-from .gimp import increase_saturation, decrease_brightness, check_file_exists, compare_triangle_positions
-from .general import check_csv, check_accessibility_tree, check_list, run_sqlite3, check_json
 from .thunderbird import check_thunderbird_prefs, check_thunderbird_filter
 from .vscode import compare_text_file, compare_config, compare_answer, is_extension_installed, check_json_settings, check_json_keybindings
-from .impress import check_image_stretch_and_center, check_slide_numbers_color, compare_pptx_files, check_strikethrough, \
-    check_for_audio, check_formula_shape
-from .impress import check_slide_orientation_Portrait, contains_mp4_video

desktop_env/evaluators/metrics/slides.py

@@ -1,6 +1,36 @@
+import logging
+import xml.etree.ElementTree as ET
+from math import sqrt
+
 from pptx import Presentation
 from pptx.util import Inches
 
+logger = logging.getLogger("desktopenv.metric.slides")
+
+
+def check_presenter_console_disable(config_file_path):
+    try:
+        tree = ET.parse(config_file_path)
+        root = tree.getroot()
+
+        namespaces = {
+            'oor': 'http://openoffice.org/2001/registry'
+        }
+
+        for item in root.findall(
+                ".//item[@oor:path='/org.openoffice.Office.Impress/Misc/Start']/prop[@oor:name='EnablePresenterScreen']",
+                namespaces):
+            # Check if the value of the configuration item indicates that the presenter console has been disabled
+            presenter_screen_enabled = item.find('value').text
+            if presenter_screen_enabled.lower() == 'false':
+                return 1.
+            else:
+                return 0.
+        return 0.
+    except Exception as e:
+        logger.error(f"Error: {e}")
+        return 0.
+
 
 def check_image_stretch_and_center(modified_ppt, original_ppt):
     # fixme: this func is overfit to this example libreoffice_impress
@@ -72,32 +102,60 @@ def compare_pptx_files(file1_path, file2_path, **options):
     prs1 = Presentation(file1_path)
     prs2 = Presentation(file2_path)
 
+    examine_number_of_slides = options.get("examine_number_of_slides", True)
+    examine_shape = options.get("examine_shape", True)
+    examine_text = options.get("examine_text", True)
+    examine_font_name = options.get("examine_font_name", True)
+    examine_font_size = options.get("examine_font_size", True)
+    examine_font_bold = options.get("examine_font_bold", True)
+    examine_font_italic = options.get("examine_font_italic", True)
+    examine_color_rgb = options.get("examine_color_rgb", True)
+    examine_font_underline = options.get("examine_font_underline", True)
+
     # compare the number of slides
-    if len(prs1.slides) != len(prs2.slides):
+    if len(prs1.slides) != len(prs2.slides) and examine_number_of_slides:
         return False
 
     # compare the content of each slide
     for slide1, slide2 in zip(prs1.slides, prs2.slides):
         # check if the shapes are the same
         for shape1, shape2 in zip(slide1.shapes, slide2.shapes):
-            if shape1.left != shape2.left or shape1.top != shape2.top or shape1.width != shape2.width or shape1.height != shape2.height:
+            if (
+                    shape1.left != shape2.left or shape1.top != shape2.top or shape1.width != shape2.width or shape1.height != shape2.height) and examine_shape:
                 return False
 
             if hasattr(shape1, "text") and hasattr(shape2, "text"):
-                if shape1.text != shape2.text:
+                if shape1.text != shape2.text and examine_text:
                     return False
 
                 # check if the paragraphs are the same
                 for para1, para2 in zip(shape1.text_frame.paragraphs, shape2.text_frame.paragraphs):
                     # check if the runs are the same
                     for run1, run2 in zip(para1.runs, para2.runs):
-                        if run1.text != run2.text:
+                        if run1.text != run2.text and examine_text:
                             return False
 
                         # check if the font properties are the same
-                        if run1.font.name != run2.font.name or run1.font.size != run2.font.size or run1.font.bold != run2.font.bold or run1.font.italic != run2.font.italic or run1.font.color.rgb != run2.font.color.rgb:
+                        if run1.font.name != run2.font.name and examine_font_name:
                             return False
 
+                        if run1.font.size != run2.font.size and examine_font_size:
+                            return False
+
+                        if run1.font.bold != run2.font.bold and examine_font_bold:
+                            return False
+
+                        if run1.font.italic != run2.font.italic and examine_font_italic:
+                            return False
+
+                        if run1.font.color.rgb != run2.font.color.rgb and examine_color_rgb:
+                            return False
+
+                        if run1.font.underline != run2.font.underline and examine_font_underline:
+                            return False
+
+                        # fixme: Actually there are more properties to be compared, but we cannot get them through pptx
+
     return True
 
 
@@ -126,32 +184,6 @@ def check_strikethrough(pptx_path, rules):
     return True
 
 
-def has_audio_on_page(slide):
-    for shape in slide.shapes:
-        if shape.shape_type == 13:
-            return True
-    return False
-
-
-def check_for_audio(prs):
-    prs = Presentation(prs)
-    for i, slide in enumerate(prs.slides):
-        if has_audio_on_page(slide):
-            return 1
-    return 0
-
-
-def check_formula_shape(prs):
-    prs = Presentation(prs)
-    slide = prs.slides[13]
-
-    for shape in slide.shapes:
-
-        if shape.has_text_frame and shape.shape_type == 1:
-            return 1
-    return 0
-
-
 def check_slide_orientation_Portrait(pptx_path):
     presentation = Presentation(pptx_path)
 
@@ -163,20 +195,40 @@ def check_slide_orientation_Portrait(pptx_path):
     return 0
 
 
-def contains_mp4_video(pptx_path):
-    prs = Presentation(pptx_path)
-    for slide in prs.slides:
-        for shape in slide.shapes:
-            if shape.shape_type == 16:
-                if shape.media_type == 3:
-                    return 1
-    return 0
+def evaluate_presentation_fill_to_rgb_distance(pptx_file, rules):
+    rgb = rules["rgb"]
+
+    def slide_fill_distance_to_rgb(_slide, _rgb):
+        fill = _slide.background.fill
+        if fill.type == 1:
+            r1, g1, b1 = fill.fore_color.rgb
+            r2, g2, b2 = _rgb
+            return sqrt((r1 - r2) ** 2 + (g1 - g2) ** 2 + (b1 - b2) ** 2) / sqrt(255 ** 2 + 255 ** 2 + 255 ** 2)
+
+        return 1
+
+    prs = Presentation(pptx_file)
+    similarity = 1 - sum(slide_fill_distance_to_rgb(slide, rgb) for slide in prs.slides) / len(prs.slides)
+    return similarity
 
 
-if __name__ == "__main__":
-    path1 = "../../任务数据/LibreOffice Impress/Change_Color_Slide_Number_gold_textbox.pptx"
-    presentation = Presentation(path1)
+def check_left_panel(accessibility_tree):
+    namespaces = {
+        'st': 'uri:deskat:state.at-spi.gnome.org',
+        'cp': 'uri:deskat:component.at-spi.gnome.org'
+    }
 
-    for i, sl in enumerate(presentation.slides):
-        for j, sh in enumerate(sl.shapes):
-            print(i, j, sh, sh.name, sh.shape_type, sh.text)
+    root = ET.fromstring(accessibility_tree)
+
+    for root_pane in root.iter('root-pane'):
+        for panel in root_pane.iter('panel'):
+            for split_pane in panel.iter('split-pane'):
+                # Get the left panel
+                if split_pane.attrib.get("{{{}}}parentcoord".format(namespaces['cp'])) == "(0, 0)":
+                    # Get the visible attribute
+                    visible = split_pane.attrib.get("{{{}}}visible".format(namespaces['st']))
+                    if visible:
+                        # decide if it is left panel
+                        return 1.
+
+    return 0.

desktop_env/evaluators/metrics/table.py

@@ -1,5 +1,5 @@
 import logging
-import operator
+#import operator
 from numbers import Number
 from typing import Any, Union, cast, Callable
 from typing import Dict, List, Tuple
@@ -14,7 +14,8 @@ from openpyxl.worksheet.worksheet import Worksheet
 #from openpyxl.worksheet.cell_range import MultiCellRange
 from openpyxl.worksheet.datavalidation import DataValidation
 
-from .utils import load_charts, load_sparklines, _match_value_to_rule
+from .utils import load_charts, load_sparklines, load_rows_or_cols, load_xlsx_styles
+from .utils import _match_value_to_rule
 
 logger = logging.getLogger("desktopenv.metric.table")
 
@@ -160,18 +161,19 @@ def compare_table(result: str, expected: str, **options) -> float:
             logger.debug("Assertion: %s[chart] == %s[chart] - %s", r["sheet_idx0"], r["sheet_idx1"], metric)
             #  }}} Compare Charts # 
 
-        elif r["type"] == "number_format":
-            #  Compare Number Formats {{{ # 
+        elif r["type"] == "style":
+            #  Compare Style (Also Conditional Formatiing) {{{ # 
             # sheet_idx0: 0 == "RI0" == "RNSheet1" | "EI0" == "ENSheet1"
             # sheet_idx1: as sheet_idx0
+            # props: list of str indicating concerned styles
 
-            sheet1: Worksheet = _load_sheet(*parse_idx(r["sheet_idx0"], xlworkbookr, xlworkbooke))
-            sheet2: Worksheet = _load_sheet(*parse_idx(r["sheet_idx1"], xlworkbookr, xlworkbooke))
-            number_formats1: List[str] = [c.number_format.lower() for col in sheet1.iter_cols() for c in col if c.data_type=="n"]
-            number_formats2: List[str] = [c.number_format.lower() for col in sheet2.iter_cols() for c in col if c.data_type=="n"]
-            metric: bool = number_formats1 == number_formats2
-            logger.debug("Assertion: %s.nf == %s.nf - %s", r["sheet_idx0"], r["sheet_idx1"], metric)
-            #  }}} Compare Number Formats # 
+            styles1: Dict[str, List[Any]] = load_xlsx_styles(*parse_idx(r["sheet_idx0"], xlworkbookr, xlworkbooke), **r)
+            styles2: Dict[str, List[Any]] = load_xlsx_styles(*parse_idx(r["sheet_idx1"], xlworkbookr, xlworkbooke), **r)
+            #number_formats1: List[str] = [c.number_format.lower() for col in sheet1.iter_cols() for c in col if c.value is not None and c.data_type=="n"]
+            #number_formats2: List[str] = [c.number_format.lower() for col in sheet2.iter_cols() for c in col if c.value is not None and c.data_type=="n"]
+            metric: bool = styles1 == styles2
+            logger.debug("Assertion: %s.style == %s.style - %s", r["sheet_idx0"], r["sheet_idx1"], metric)
+            #  }}} Compare Style (Also Conditional Formatiing) # 
 
         elif r["type"] == "freeze":
             #  Compare Freezing {{{ # 
@@ -203,7 +205,7 @@ def compare_table(result: str, expected: str, **options) -> float:
         elif r["type"] == "data_validation":
             #  Check Data Validation {{{ # 
             # sheet_idx: 0 == "RI0" == "RNSheet1" | "EI0" == "ENSheet1"
-            # dv_props: list of dict like {attribute: "method": str, "ref": anythin}
+            # dv_props: list of dict like {attribute: {"method": str, "ref": anything}}
             #   available attributes:
             #     * ranges
             #     * type
@@ -224,14 +226,14 @@ def compare_table(result: str, expected: str, **options) -> float:
             sheet: Worksheet = _load_sheet(*parse_idx(r["sheet_idx"], xlworkbookr, xlworkbooke))
             data_validators: List[DataValidation] = sheet.data_validations.dataValidation
 
-            total_metric = True
+            total_metric = len(data_validators)>=len(r["dv_props"])
             for dat_vldt in data_validators:
                 metric = False
-                for r in r["dv_props"]:
+                for prpt in r["dv_props"]:
                     metric = metric or all( _match_value_to_rule( getattr(dat_vldt, attrbt)
                                                                 , mr
                                                                 )\
-                                        for attrbt, mr in r.items()
+                                        for attrbt, mr in prpt.items()
                                           )
                     if metric:
                         break
@@ -243,6 +245,44 @@ def compare_table(result: str, expected: str, **options) -> float:
             metric: bool = total_metric
             #  }}} Check Data Validation # 
 
+        elif r["type"] == "row_props":
+            #  Check Row Properties {{{ # 
+            # sheet_idx0: 0 == "RI0" == "RNSheet1" | "EI0" == "ENSheet1"
+            # sheet_idx1: as sheet_idx0
+            # props: list of str, see utils.load_rows_or_cols
+
+            rows1: Dict[str, Any] = load_rows_or_cols( *parse_idx(r["sheet_idx0"], xlworkbookr, xlworkbooke)
+                                                     , obj="row"
+                                                     , **r
+                                                     )
+            rows2: Dict[str, Any] = load_rows_or_cols( *parse_idx(r["sheet_idx1"], xlworkbookr, xlworkbooke)
+                                                     , obj="row"
+                                                     , **r
+                                                     )
+            logger.debug("Rows1: %s", repr(rows1))
+            logger.debug("Rows2: %s", repr(rows2))
+            metric: bool = rows1 == rows2
+            logger.debug("Assertion: %s[rows] == %s[rows] - %s", r["sheet_idx0"], r["sheet_idx1"], metric)
+            #  }}} Check Row Properties # 
+
+        elif r["type"] == "col_props":
+            #  Check Row Properties {{{ # 
+            # sheet_idx0: 0 == "RI0" == "RNSheet1" | "EI0" == "ENSheet1"
+            # sheet_idx1: as sheet_idx0
+            # props: list of str, see utils.load_rows_or_cols
+
+            cols1: Dict[str, Any] = load_rows_or_cols( *parse_idx(r["sheet_idx0"], xlworkbookr, xlworkbooke)
+                                                     , obj="column"
+                                                     , **r
+                                                     )
+            cols2: Dict[str, Any] = load_rows_or_cols( *parse_idx(r["sheet_idx1"], xlworkbookr, xlworkbooke)
+                                                     , obj="column"
+                                                     , **r
+                                                     )
+            metric: bool = cols1 == cols2
+            logger.debug("Assertion: %s[cols] == %s[cols] - %s", r["sheet_idx0"], r["sheet_idx1"], metric)
+            #  }}} Check Row Properties # 
+
         else:
             raise NotImplementedError("Unimplemented sheet check: {:}".format(r["type"]))
 
@@ -254,15 +294,48 @@ def compare_table(result: str, expected: str, **options) -> float:
     #  }}} function compare_table # 
 
 if __name__ == '__main__':
-    path1 = "../../任务数据/LibreOffice Calc/Freeze_row_column.xlsx"
-    path2 = "../../任务数据/LibreOffice Calc/Freeze_row_column_gold.xlsx"
+    import datetime
+    import sys
+
+    logger = logging.getLogger()
+    logger.setLevel(logging.DEBUG)
+
+    datetime_str: str = datetime.datetime.now().strftime("%Y%m%d@%H%M%S")
+
+    file_handler = logging.FileHandler(os.path.join("logs", "normal-{:}.log".format(datetime_str)))
+    debug_handler = logging.FileHandler(os.path.join("logs", "debug-{:}.log".format(datetime_str)))
+    stdout_handler = logging.StreamHandler(sys.stdout)
+    sdebug_handler = logging.FileHandler(os.path.join("logs", "sdebug-{:}.log".format(datetime_str)))
+
+    file_handler.setLevel(logging.INFO)
+    debug_handler.setLevel(logging.DEBUG)
+    stdout_handler.setLevel(logging.INFO)
+    sdebug_handler.setLevel(logging.DEBUG)
+
+    formatter = logging.Formatter(fmt="\x1b[1;33m[%(asctime)s \x1b[31m%(levelname)s \x1b[32m%(module)s/%(lineno)d-%(processName)s\x1b[1;33m] \x1b[0m%(message)s")
+    file_handler.setFormatter(formatter)
+    debug_handler.setFormatter(formatter)
+    stdout_handler.setFormatter(formatter)
+    sdebug_handler.setFormatter(formatter)
+
+    stdout_handler.addFilter(logging.Filter("desktopenv"))
+    sdebug_handler.addFilter(logging.Filter("desktopenv"))
+
+    logger.addHandler(file_handler)
+    logger.addHandler(debug_handler)
+    logger.addHandler(stdout_handler)
+    logger.addHandler(sdebug_handler)
+
+    path1 = "../../任务数据/LibreOffice Calc/Calendar_Highlight_Weekend_Days.xlsx"
+    path2 = "../../任务数据/LibreOffice Calc/Calendar_Highlight_Weekend_Days_gold.xlsx"
     rules = [ { "type": "sheet_data"
               , "sheet_idx0": 0
               , "sheet_idx1": "EI0"
               }
-            , { "type": "freeze"
+            , { "type": "style"
               , "sheet_idx0": 0
               , "sheet_idx1": "EI0"
+              , "props": ["bgcolor"]
               }
             ]
     print( compare_table( path1, path2
@@ -274,17 +347,31 @@ if __name__ == '__main__':
                         )
          )
 
-    #path = "../../任务数据/LibreOffice Calc/Order_Id_Mark_Pass_Fail_gold.xlsx"
-    #print( check_data_validations( path, [ { "ranges": { "method": "spreadsheet_range"
-                                                       #, "ref": ["D2:D29", "D2:D1048576"]
-                                                       #}
-                                           #, "type": { "method": "eq"
-                                                     #, "ref": "list"
-                                                     #}
-                                           #, "formula1": { "method": "str_set_eq"
-                                                         #, "ref": ["Pass", "Fail", "Held"]
-                                                         #}
-                                           #}
-                                         #]
-                                 #)
-         #)
+    # Row Properties
+    #path1 = "../../任务数据/LibreOffice Calc/Date_Budget_Variance_HideNA.xlsx"
+    #path2 = "../../任务数据/LibreOffice Calc/Date_Budget_Variance_HideNA_gold.xlsx"
+    #workbook: Workbook = openpyxl.load_workbook(filename=path1)
+    #worksheet: Worksheet = workbook.active
+    #for r_no, dms in worksheet.column_dimensions.items():
+        #print(r_no, type(r_no), type(dms), dms.hidden)
+
+    # Conditional Formats
+    #import formulas
+    #path1 = "../../任务数据/LibreOffice Calc/Calendar_Highlight_Weekend_Days.xlsx"
+    #path2 = "../../任务数据/LibreOffice Calc/Calendar_Highlight_Weekend_Days_gold.xlsx"
+    #path3 = "../../任务数据/LibreOffice Calc/Calendar_Highlight_Weekend_Days_gold_test.xlsx"
+    #workbook: Workbook = openpyxl.load_workbook(filename=path2)
+    #worksheet: Worksheet = workbook.active
+    #print(worksheet.conditional_formatting)
+    #for itm in worksheet.conditional_formatting:
+        #print(itm.cells)
+        #for r in itm.rules:
+            #print( r.type, r.formula, r.dxf.font.color.rgb
+                 #, r.dxf.fill.fgColor.rgb, r.dxf.fill.bgColor.rgb
+                 #)
+            #condition = formulas.Parser().ast("=" + r.formula[0])[1].compile()
+            ##print(r.type, r.operator, r.dxfId, r.dxf)
+            #for r in itm.cells:
+                #for c in r.cells:
+                    #value = worksheet.cell(row=c[0], column=c[1]).value
+                    #print(value, condition(str(value)))

desktop_env/evaluators/metrics/utils.py

@@ -1,6 +1,6 @@
 import logging
 import zipfile
-from typing import Any, TypeVar, Union, Iterable, Optional
+from typing import Any, TypeVar, Union, Iterable, Optional, Callable
 from typing import Dict, List, Set, Match
 from urllib.parse import urlparse, urlunparse
 import re
@@ -17,6 +17,12 @@ from openpyxl import Workbook
 from openpyxl.chart._chart import ChartBase
 from openpyxl.worksheet.worksheet import Worksheet
 from openpyxl.worksheet.cell_range import MultiCellRange
+from openpyxl.worksheet.dimensions import DimensionHolder
+from openpyxl.formatting.formatting import ConditionalFormattingList
+#from openpyxl.utils import get_column_letter
+from openpyxl.cell.cell import Cell
+from openpyxl.styles.differential import DifferentialStyle
+import formulas
 
 V = TypeVar("Value")
 
@@ -31,9 +37,8 @@ _xlsx_ns_imapping = dict(map(lambda itm: (itm[1], itm[0]), _xlsx_namespaces))
 _sheet_name_selector = lxml.cssselect.CSSSelector("oo|sheets>oo|sheet", namespaces=_xlsx_ns_mapping)
 _sparklines_selector = lxml.cssselect.CSSSelector("x14|sparkline", namespaces=_xlsx_ns_mapping)
 def load_sparklines(xlsx_file: str, sheet_name: str) -> Dict[str, str]:
+    #  function load_sparklines {{{ # 
     """
-    This function modifies data_frame in-place
-
     Args:
         xlsx_file (str): path to xlsx
         sheet_name (str): sheet name
@@ -64,6 +69,7 @@ def load_sparklines(xlsx_file: str, sheet_name: str) -> Dict[str, str]:
                                                                )
         sparklines_dict[sparkline["x14:sparkline"]["xm:sqref"]] = sparkline["x14:sparkline"]["xm:f"]
     return sparklines_dict
+    #  }}} function load_sparklines # 
 
 
 # Available Chart Properties:
@@ -75,6 +81,7 @@ def load_sparklines(xlsx_file: str, sheet_name: str) -> Dict[str, str]:
 # direction: "bar" (hori) | "col" (vert)
 # xtitle, ytitle, ztitle: str
 def load_charts(xlsx_file: Workbook, sheet_name: str, **options) -> Dict[str, Any]:
+    #  function load_charts {{{ # 
     """
     Args:
         xlsx_file (Workbook): concerned excel book
@@ -83,7 +90,12 @@ def load_charts(xlsx_file: Workbook, sheet_name: str, **options) -> Dict[str, An
           giving the concerned chart properties
 
     Returns:
-        Dict[str, Any]: information of charts
+        Dict[str, Any]: information of charts, dict like
+          {
+            <str representing data source>: {
+                <str as property>: anything
+            }
+          }
     """
 
     # workbook: Workbook = openpyxl.load_workbook(filename=xlsx_file)
@@ -140,7 +152,132 @@ def load_charts(xlsx_file: Workbook, sheet_name: str, **options) -> Dict[str, An
             info["ztitle"] = ch.z_axis.title.tx.rich.p[0].r[0].t
         chart_set[series] = info
     return chart_set
+    #  }}} function load_charts # 
 
+# Supported Styles:
+# number_format
+# font_name - str
+# font_family - float
+# font_color - in aRGB, e.g., FF000000 is black
+# font_bold - bool
+# font_italic - bool
+# fill_type - "patternFill" | "gradientFill"
+# bgcolor - in aRGB, e.g., FFFF0000 is red
+# fgcolor - in aRGB, e.g., FF00FFFF is yellow
+def _read_cell_style(style_name: str, cell: Cell, diff_style: Optional[DifferentialStyle] = None) -> Any:
+    if style_name=="number_format":
+        return (cell.number_format if diff_style is None else diff_style.numFmt.formatCode)\
+               if cell.value is not None and cell.data_type=="n" else None
+    elif style_name=="font_name":
+        return (diff_style or cell).font.name if cell.value is not None else None
+    elif style_name=="font_family":
+        return (diff_style or cell).font.family if cell.value is not None else None
+    elif style_name=="font_color":
+        return (diff_style or cell).font.color.rgb if cell.value is not None else None
+    elif style_name=="font_bold":
+        return (diff_style or cell).font.bold if cell.value is not None else None
+    elif style_name=="font_italic":
+        return (diff_style or cell).font.italic if cell.value is not None else None
+    elif style_name=="fill_type":
+        return (diff_style or cell).fill.tagname
+    elif style_name=="bgcolor":
+        return (diff_style or cell).fill.bgColor.rgb
+    elif style_name=="fgcolor":
+        return (diff_style or cell).fill.fgColor.rgb
+    else:
+        raise NotImplementedError("Unsupported Style: {:}".format(style_name))
+
+def load_xlsx_styles(xlsx_file: Workbook, sheet_name: str, **options) -> Dict[str, List[Any]]:
+    #  function load_xlsx_styles {{{ # 
+    """
+    Args:
+        xlsx_file (Workbook): concerned excel book
+        sheet_name (str): sheet name
+        options (Dict[str, List[str]): dick like {"props": list of str} giving
+          the concerned styles
+
+    Returns:
+        Dict[str, List[Any]]: dict like
+          {
+            <str as cell coordinates>: list of anything indicating concerned
+              property values
+          }
+    """
+
+    worksheet: Worksheet = xlsx_file[sheet_name]
+
+    style_dict: Dict[str, List[Any]] = {}
+    concerned_styles: List[str] = options.get("props", [])
+
+    # Handles Cell Styles
+    for col in worksheet.iter_cols():
+        for c in col:
+            style_list: List[Any] = []
+            for st in concerned_styles:
+                style_list.append(_read_cell_style(st, c))
+            style_dict[c.coordinate] = style_list
+
+    # Handles Conditional Formatting
+    conditional_formattings: ConditionalFormattingList = worksheet.conditional_formatting
+    formula_parser = formulas.Parser()
+    for fmt in conditional_formattings:
+        for r in fmt.rules:
+            active_cells: List[Cell] = []
+            if r.type == "expression":
+                condition: Callable[[str], bool] = formula_parser.ast("=" + r.formula[0])[1].compile()
+                for rge in fmt.cells:
+                    for c in rge.cells:
+                        cell: Cell = worksheet.cell(row=c[0], column=c[1])
+                        if condition(str(cell.value)):
+                            active_cells.append(cell)
+            else:
+                raise NotImplementedError("Not Implemented Condition Type: {:}".format(r.type))
+
+            for c in active_cells:
+                style_dict[c.coordinate] = [_read_cell_style(st, c, r.dxf) for st in concerned_styles]
+
+    return style_dict
+    #  }}} function load_xlsx_styles # 
+
+# Available Row Properties:
+# hidden
+# collapsed
+# height
+#
+# Available Column Properties:
+# width
+# auto_size
+# hidden
+# collapsed
+# min
+# max
+def load_rows_or_cols(xlsx_file: Workbook, sheet_name: str, **options)\
+        -> Dict[Union[int, str], Dict[str, Any]]:
+    #  function load_rows_or_cols {{{ # 
+    """
+    Args:
+        xlsx_file (Workbook): concerned excel book
+        sheet_name (str): sheet name
+        options (Dict[str, List[str]]): dict like
+          {"obj": "row" | "column", "props": list of str} giving the concerned
+          row/column properties
+
+    Returns:
+        Dict[Union[int, str], Dict[str, Any]]: row/column information
+    """
+
+    worksheet: Worksheet = xlsx_file[sheet_name]
+    objs: DimensionHolder = getattr(worksheet, "{:}_dimensions".format(options["obj"]))
+
+    obj_set: Dict[int, Any] = {}
+    obj_props: Set[str] = set(options.get("props", []))
+    for obj_no, obj_dms in objs.items():
+        info_dict: Dict[str, Any] = {}
+        for prop in obj_props:
+            info_dict[prop] = getattr(obj_dms, prop)
+        obj_set[obj_no] = info_dict
+    return obj_set
+    #  }}} function load_rows_or_cols # 
 
 def _match_record(pattern: Dict[str, Any], item: Dict[str, Any]) -> bool:
     return all(k in item and item[k] == val for k, val in pattern.items())

desktop_env/evaluators/metrics/vlc.py

@@ -10,6 +10,8 @@ import imagehash
 import librosa
 import numpy as np
 from PIL import Image
+from fastdtw import fastdtw
+from scipy.spatial.distance import cosine
 from skimage.metrics import structural_similarity as ssim
 
 logger = logging.getLogger("desktopenv.metrics.vlc")
@@ -111,11 +113,10 @@ def compare_images(image1_path, image2_path):
     return similarity_index
 
 
-def compare_audios(audio_path_1, audio_path_2, max_distance=1000):
+def compare_audios(audio_path_1, audio_path_2):
     """
     Compare two audio files and return a similarity score in the range [0, 1].
     audio_path_1, audio_path_2: paths to the audio files to compare
-    max_distance: an empirically determined maximum expected DTW distance
     """
     # Example Usage:
     # similarity = compare_audios_simple('path_to_audio1.mp3', 'path_to_audio2.mp3')
@@ -125,21 +126,31 @@ def compare_audios(audio_path_1, audio_path_2, max_distance=1000):
     if not audio_path_1 or not audio_path_2:
         return 0
 
+    # Load the audio files and extract MFCC features
     y1, sr1 = librosa.load(audio_path_1)
-    y2, sr2 = librosa.load(audio_path_2)
-
-    # Extract MFCC features
     mfcc1 = librosa.feature.mfcc(y=y1, sr=sr1)
+
+    y2, sr2 = librosa.load(audio_path_2)
     mfcc2 = librosa.feature.mfcc(y=y2, sr=sr2)
 
-    # Compute Dynamic Time Warping distance
-    distance, path = librosa.sequence.dtw(mfcc1.T, mfcc2.T)
+    # Normalize the MFCC features
+    mfcc1 = librosa.util.normalize(mfcc1, axis=1)
+    mfcc2 = librosa.util.normalize(mfcc2, axis=1)
 
-    # Normalize distance to get a similarity score
-    normalized_distance = np.mean(distance) / max_distance
-    similarity_score = 1 - min(normalized_distance, 1)  # Ensure the score is within [0, 1]
+    # Define a lambda function to compute cosine distance
+    dist_func = lambda x, y: cosine(x, y)
 
-    return similarity_score
+    # Use the DTW algorithm to find the best alignment path
+    distance, path = fastdtw(mfcc1.T, mfcc2.T, dist=dist_func)
+
+    # Calculate the similarity score, here we use 1/(1+distance) to convert distance to a similarity score
+    similarity = 1 / (1 + distance)
+
+    return similarity
+
+
+def compare_audios_by_dl_model(audio_path_1, audio_path_2):
+    pass
 
 
 def compare_videos(video_path1, video_path2, max_frames_to_check=100, threshold=5):