Merge branch 'zdy'

desktop_env/evaluators/getters/file.py

@@ -1,50 +1,92 @@
 import os
-from typing import Dict
-from typing import Optional
+from typing import Dict, List, Set
+from typing import Optional, Any, Union
 
 import requests
 
 
-def get_cloud_file(env, config: Dict[str, str]) -> str:
+def get_cloud_file(env, config: Dict[str, Any]) -> Union[str, List[str]]:
     """
     Config:
-        path (str): the url to download from
-        dest (str): file name of the downloaded file
+        path (str|List[str]): the url to download from
+        dest (str|List[str])): file name of the downloaded file
+        multi (bool) : optional. if path and dest are lists providing
+          information of multiple files. defaults to False
+        gives (List[int]): optional. defaults to [0]. which files are directly
+          returned to the metric. if len==1, str is returned; else, list is
+          returned.
     """
 
-    _path = os.path.join(env.cache_dir, config["dest"])
-    if os.path.exists(_path):
-        return _path
+    if not config.get("multi", False):
+        paths: List[str] = [config["path"]]
+        dests: List[str] = [config["dest"]]
+    else:
+        paths: List[str] = config["path"]
+        dests: List[str] = config["dest"]
+    cache_paths: List[str] = []
 
-    url = config["path"]
-    response = requests.get(url, stream=True)
-    response.raise_for_status()
+    gives: Set[int] = set(config.get("gives", [0]))
 
-    with open(_path, 'wb') as f:
-        for chunk in response.iter_content(chunk_size=8192):
-            if chunk:
-                f.write(chunk)
+    for i, (p, d) in enumerate(zip(paths, dests)):
+        _path = os.path.join(env.cache_dir, d)
+        if i in gives:
+            cache_paths.append(_path)
 
-    return _path
+        if os.path.exists(_path):
+            #return _path
+            continue
+
+        url = p
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        with open(_path, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+
+    return cache_paths[0] if len(cache_paths)==1 else cache_paths
 
 
-def get_vm_file(env, config: Dict[str, str]) -> Optional[str]:
+def get_vm_file(env, config: Dict[str, Any]) -> Union[Optional[str], List[Optional[str]]]:
     """
     Config:
         path (str): absolute path on the VM to fetch
         dest (str): file name of the downloaded file
+        multi (bool) : optional. if path and dest are lists providing
+          information of multiple files. defaults to False
+        gives (List[int]): optional. defaults to [0]. which files are directly
+          returned to the metric. if len==1, str is returned; else, list is
+          returned.
     """
 
-    _path = os.path.join(env.cache_dir, config["dest"])
+    if not config.get("multi", False):
+        paths: List[str] = [config["path"]]
+        dests: List[str] = [config["dest"]]
+    else:
+        paths: List[str] = config["path"]
+        dests: List[str] = config["dest"]
+    cache_paths: List[str] = []
 
-    file = env.controller.get_file(config["path"])
-    if file is None:
-        return None
-        # raise FileNotFoundError("File not found on VM: {:}".format(config["path"]))
-    with open(_path, "wb") as f:
-        f.write(file)
+    gives: Set[int] = set(config.get("gives", [0]))
 
-    return _path
+    for i, (p, d) in enumerate(zip(paths, dests)):
+        _path = os.path.join(env.cache_dir, d)
+
+        file = env.controller.get_file(p)
+        if file is None:
+            #return None
+            # raise FileNotFoundError("File not found on VM: {:}".format(config["path"]))
+            if i in gives:
+                cache_paths.append(None)
+            continue
+
+        if i in gives:
+            cache_paths.append(_path)
+        with open(_path, "wb") as f:
+            f.write(file)
+
+    return cache_paths[0] if len(cache_paths)==1 else cache_paths
 
 
 def get_cache_file(env, config: Dict[str, str]) -> str:

desktop_env/evaluators/metrics/table.py

@@ -3,6 +3,8 @@ import operator
 from numbers import Number
 from typing import Any, Union
 from typing import Dict, List
+import os.path
+import itertools
 
 import openpyxl
 import pandas as pd
@@ -26,6 +28,7 @@ def compare_table(actual: str, expected: str, **options) -> float:
                 * chart
                 * number_format
             "chart_props": list of str, giving the converned chart properties
+            "as_shown": bool, TODO
           }
 
     Return:
@@ -35,10 +38,35 @@ def compare_table(actual: str, expected: str, **options) -> float:
     if actual is None:
         return 0.
 
-    df1 = pd.read_excel(expected)
-    df2 = pd.read_excel(actual)
-    metric: bool = df1.equals(df2)
-    logger.debug("Normal Contents Metric: {:}".format(metric))
+    if options.get("as_shown", False):
+        expected_csv: str = os.path.splitext(expected)[0] + ".csv"
+        actual_csv: str = os.path.splitext(actual)[0] + ".csv"
+
+        with open(expected_csv) as f:
+            expected_lines: List[str] = list( itertools.dropwhile( lambda l: len(l)==0
+                                                                 , map( lambda l: l.strip()
+                                                                      , reversed(f.read().splitlines())
+                                                                      )
+                                                                 )
+                                            )
+            if options.get("ignore_case", False):
+                expected_lines = [l.lower() for l in expected_lines]
+        with open(actual_csv) as f:
+            actual_lines: List[str] = list( itertools.dropwhile( lambda l: len(l)==0
+                                                               , map( lambda l: l.strip()
+                                                                    , reversed(f.read().splitlines())
+                                                                    )
+                                                               )
+                                          )
+            if options.get("ignore_case", False):
+                actual_lines = [l.lower() for l in actual_lines]
+        metric: bool = expected_lines==actual_lines
+        logger.debug("Content Metric just as shown: %s", metric)
+    else:
+        df1 = pd.read_excel(expected)
+        df2 = pd.read_excel(actual)
+        metric: bool = df1.equals(df2)
+        logger.debug("Normal Content Metric: {:}".format(metric))
 
     features: List[str] = options.get("features", [])
     for ftr in features:
@@ -219,6 +247,8 @@ if __name__ == '__main__':
     # print(check_zoom(path1, {"relation": "lt", "ref_value": 100}))
     # print(check_zoom(path2, {"relation": "lt", "ref_value": 100}))
 
-    path1 = "../../任务数据/LibreOffice Calc/Padding_Decimals_In_Formular_gold.xlsx"
-    data_frame: pd.DataFrame = pd.read_excel(path1)
-    print(data_frame)
+    path1 = "../../任务数据/LibreOffice Calc/Customers_New_7digit_Id.xlsx"
+    path2 = "../../任务数据/LibreOffice Calc/Customers_New_7digit_Id_gold.xlsx"
+    #data_frame: pd.DataFrame = pd.read_excel(path1)
+    #print(data_frame)
+    print(compare_table(path1, path2, as_shown=True))