Merge pull request #3 from philips-software/bugfix

Bugfix

README.md

@@ -58,6 +58,24 @@ out_put = core_extractor.extractor (r"path_to_repo/code")
 print(out_put)
 ```
 
+- To exclude specific files from repository.
+
+```sh
+from functiondefextractor import core_extractor
+out_put = core_extractor.extractor (r"path_to_repo/code",
+                     regex_pattern=r'*\test\*, *.java')
+print(out_put)
+```
+
+Sample regex patterns: (Note: replace # with *)
+
+1. '#.java' =>  to exclude all java files in a repository.
+
+2. '#/test/#' => to exclude test folder and files in it.
+
+3. '#/src/#/*.cpp' => to exclude all cpp files in src and
+    it's sub directories
+
 - To extract functions based on annotation.
 
 ```sh
@@ -81,10 +99,10 @@ print(out_put)
 For example to search assert, suppress warnings patterns.
 
 ```sh
-from functiondefextractor import core_extractor
+from functiondefextractor import condition_checker
 out_put = core_extractor.check_condition
           ("@SupressWarning", r"path_to_excelfile/dataframe", "(")
-print(out_put)
+print(out_put[0], out_put[1])
 ```
 
 ### Commandline
@@ -95,11 +113,18 @@ print(out_put)
 >>>python -m functiondefextractor.extractor_cmd --p path/to/repo
 ```
 
+- To ignore files from repo using regex pattern.
+
+```sh
+>>>python -m functiondefextractor.extractor_cmd --p path/to/repo
+                                        --i '*.java, *.cpp'
+```
+
 - To analyse various patterns in the code based on given condition.
 
 ```sh
 >>>python -m functiondefextractor.extractor_cmd
-             --c "@Assert" --e path/to/excel/dataframe --s "("
+             --c "Assert" --e path/to/excel --s "("
 ```
 
 - Help option can be found at,  
@@ -108,6 +133,58 @@ print(out_put)
 >>>python -m functiondefextractor.extractor_cmd -h
 ```
 
+### Sample use cases
+
+- To extract all functions from a repository
+
+```sh
+>>>python -m functiondefextractor.extractor_cmd --p path/to/repo
+```
+
+```sh
+from functiondefextractor import core_extractor
+out_put = core_extractor.extractor (r"path_to_repo/code")
+print(out_put)
+```
+
+- To extract all functions with "@Test" annotation
+  excluding all ".cpp" files in the repository
+
+```sh
+>>>python -m functiondefextractor.extractor_cmd --p path/to/repo
+                --a "@Test" --i '*.cpp'
+```
+
+```sh
+from functiondefextractor import core_extractor
+out_put = core_extractor.extractor
+          (r"path_to_repo/code", annot="@Test", regex_pattern=r'*.cpp')
+print(out_put)
+```
+
+Note:
+
+1. functionstartwith argument can be used to specifically extract code
+from required functions whose names starts with "test_" or what ever name
+user is interested in.
+
+2. delta and annot arguments together can be used to extract required number
+of lines below and above the given annotation/keyword.
+
+- To analyze various patterns present in extracted code
+
+```sh
+>>>python -m functiondefextractor.extractor_cmd
+             --c "Assert" --e path/to/excel --s "("
+```
+
+```sh
+from functiondefextractor import condition_checker
+out_put = core_extractor.check_condition
+          ("@SupressWarning", r"path_to_excelfile/dataframe", "(")
+print(out_put[0], out_put[1])
+```
+
 ### Output
 
 - Executing functiondefextractor to extract functions from
@@ -117,9 +194,10 @@ print(out_put)
 - Using functiondefextractor to extract functions from code would return
  a dataframe with same content as excel file.
 
-- When functiondefextractor is executed to analyse patterns in code, an excel file
- with multiple sheets would be generated which contains the requested patterns and
- pivot table. Also an html file with pivot table of the same would be generated.
+- When functiondefextractor is executed from script to analyse patterns in code,
+ a tuple with 2 data frames would be generated which contains the requested pattern
+ statements with their count in various functions and a pivot table of the
+ same respectively.
 
 ## Contact
 

build_scripts/dependencies_static_analysis_test_cov.py

@@ -90,7 +90,7 @@ def check_dead_code():
     """
     checks the repo for dead code with minimum confidence 100
     """
-    call_subprocess("python3 -m vulture --min-confidence 60 "
+    call_subprocess("python -m vulture --min-confidence 60 "
                     "functiondefextractor test build_scripts whitelist.py")
     print("Stage dead code detection -- COMPLETED & PASSED  --")
 

functiondefextractor/condition_checker.py

@@ -21,18 +21,18 @@ def check_condition(condition, file_path_dataframe, splitter=None):
     test_assert = condition
     if ['Uniq ID'] not in data.columns.ravel():
         return "Couldn't find Uniq ID column"
-    data = pd.DataFrame(data, columns=['Uniq ID', 'Code']).set_index("Uniq ID")
+    data = pd.DataFrame(data, columns=['Uniq ID', 'Code'])
     specifier_column = []
     spe_data = ""
     for i in range(len(data)):
-        for line in str(data.iat[i, 0]).splitlines():
+        for line in str(data.iat[i, 1]).splitlines():
             if test_assert.upper() in line.strip().upper():
                 spe_data = spe_data + line.strip() + os.linesep
         specifier_column.append(spe_data)
         spe_data = ""
     data['Count of %s in function' % test_assert] = data["Code"].str.upper().str.count(test_assert.upper())
     data["%s Statements" % test_assert] = specifier_column
-    get_pivot_table_result(data, test_assert, splitter, file_path_dataframe)
+    return get_pivot_table_result(data, test_assert, splitter, file_path_dataframe)
 
 
 def get_pivot_table_result(data, test_assert, splitter, file_path):
@@ -47,16 +47,20 @@ def get_pivot_table_result(data, test_assert, splitter, file_path):
         data["%s Statements" % test_assert] = data["%s Statements" % test_assert].apply(lambda x: x.split(splitter)[0])
     data_table = data.groupby("%s Statements" % test_assert).count().iloc[:, 1]
     data_table = data_table.to_frame()
-    data_table = data_table.rename({'Count of %s in function' % test_assert:
-                                        'Different %s pattern counts' % test_assert}, axis='columns')
+    data_table = data_table.rename({'Code': 'Different %s pattern counts' % test_assert}, axis='columns')
     data_table = data_table.reset_index()
     data_table["%s Statements" % test_assert] = data_table["%s Statements" % test_assert].str.wrap(200)
     if data_table.iat[0, 0] == '':  # pragma: no mutate
         data_table = data_table.drop([data_table.index[0]])
-    html_file_path = os.path.join(os.path.dirname(file_path), 'Pivot_table_%s.html') % test_assert.strip("@")
-    writer = pd.ExcelWriter(os.path.join(os.path.dirname(file_path), 'Pattern_Result_%s.xlsx')
-                            % test_assert.strip("@"), engine='xlsxwriter')
-    data.to_excel(writer, sheet_name='Data')  # pragma: no mutate
-    data_table.to_excel(writer, sheet_name='Pivot Table')  # pragma: no mutate
-    data_table.to_html(html_file_path)
-    writer.save()
+    if str(type(file_path)) != "<class 'pandas.core.frame.DataFrame'>":
+        html_file_path = os.path.join(os.path.dirname(file_path), 'Pivot_table_%s.html') % test_assert.strip("@")
+        writer = pd.ExcelWriter(os.path.join(os.path.dirname(file_path), 'Pattern_Result_%s.xlsx')
+                                % test_assert.strip("@"), engine='xlsxwriter')
+        data.to_excel(writer, sheet_name='Data')  # pragma: no mutate
+        data_table.to_excel(writer, sheet_name='Pivot Table')  # pragma: no mutate
+        data_table.to_html(html_file_path)
+        writer.save()
+        ret_val = "Report files successfully generated at input path"
+    else:
+        ret_val = data, data_table
+    return ret_val