Check XML validation in Notepad++ build system

1. Added xml syntax check via python script just for the win32 debug build because there already the functionlist check happens.
2. Fixed an issue found for perl.

Fix #9330, close #9339

PowerEditor/installer/APIs/perl.xml

@@ -255,7 +255,7 @@
 		<KeyWord name="given" />
 		<KeyWord name="glob" func="yes"><Overload retVal="" descr="expand filenames using wildcards"><Param name="EXPR" /></Overload><Overload retVal="" descr="expand filenames using wildcards"><Param name="" /></Overload></KeyWord>
 		<KeyWord name="gmtime" func="yes"><Overload retVal="" descr="convert UNIX time into record or string using Greenwich time"><Param name="EXPR" /></Overload><Overload retVal="" descr="convert UNIX time into record or string using Greenwich time"><Param name="" /></Overload></KeyWord>
-		<KeyWord name="goto" func="yes"><Overload retVal="" descr="create spaghetti code"><Param name="&NAME" /></Overload><Overload retVal="" descr="create spaghetti code"><Param name="EXPR" /></Overload><Overload retVal="" descr="create spaghetti code"><Param name="LABEL" /></Overload></KeyWord>
+		<KeyWord name="goto" func="yes"><Overload retVal="" descr="create spaghetti code"><Param name="&amp;NAME" /></Overload><Overload retVal="" descr="create spaghetti code"><Param name="EXPR" /></Overload><Overload retVal="" descr="create spaghetti code"><Param name="LABEL" /></Overload></KeyWord>
 		<KeyWord name="grep" func="yes"><Overload retVal="" descr="locate elements in a list test true against a given criterion"><Param name="BLOCK LIST" /></Overload><Overload retVal="" descr="locate elements in a list test true against a given criterion"><Param name="EXPR" /><Param name="LIST" /></Overload></KeyWord>
 		<KeyWord name="groove" />
 		<KeyWord name="gt" />

appveyor.yml

@@ -7,6 +7,7 @@ environment:
     - platform: Win32
       archi: x86
       platform_input: Win32
+      PYTHON: "C:\\Python38"
 
     - platform: x64
       archi: amd64
@@ -34,7 +35,7 @@ build_script:
     - if "%configuration%"=="Unicode Release" set scintilla_debug=
     - if "%archi%" NEQ "" nmake SUPPORT_XP=1 %scintilla_debug% -f scintilla.mak
     - if "%Platform%"=="mingw-w64_810_X64" mingw32-make -j%NUMBER_OF_PROCESSORS%
-    
+
     - cd "%APPVEYOR_BUILD_FOLDER%"\PowerEditor\visual.net\
     - if "%archi%" NEQ "" msbuild notepadPlus.vcxproj /p:configuration="%configuration%" /p:platform="%platform_input%" /logger:"C:\Program Files\AppVeyor\BuildAgent\Appveyor.MSBuildLogger.dll"
     - if "%Platform%"=="mingw-w64_810_X64" cd c:\projects\notepad-plus-plus\PowerEditor\gcc\ & mingw32-make -j%NUMBER_OF_PROCESSORS%
@@ -42,6 +43,11 @@ build_script:
 
 after_build:
     - cd "%APPVEYOR_BUILD_FOLDER%"
+    #xml files syntax checks
+    - if "%platform_input%"=="Win32" if "%configuration%"=="Unicode Debug" SET PATH=%PYTHON%;%PYTHON%\Scripts;%PATH%
+    - if "%platform_input%"=="Win32" if "%configuration%"=="Unicode Debug" python -m pip install requests rfc3987 pywin32 lxml
+    - if "%platform_input%"=="Win32" if "%configuration%"=="Unicode Debug" call python validator_xml.py
+
     - ps: >-
         $nppFileName = "Notepad++.$env:PLATFORM_INPUT.$env:CONFIGURATION.exe"
 

validator_xml.py

@@ -0,0 +1,114 @@
+#!/usr/local/bin/python3
+
+import os
+import io
+import sys
+
+import requests
+from hashlib import sha256
+from lxml import etree
+
+api_url = os.environ.get('APPVEYOR_API_URL')
+has_error = False
+
+
+def post_error(message):
+    global has_error
+
+    has_error = True
+
+    message = {
+        "message": message,
+        "category": "error",
+        "details": ""
+    }
+
+    if api_url:
+        requests.post(api_url + "api/build/messages", json=message)
+    else:
+        from pprint import pprint
+        pprint(message)
+
+
+def parse_xml_file(filename_xml):
+
+    # open and read schema file
+    #with open(filename_xsd, 'r') as schema_file:
+        #schema_to_check = schema_file.read()
+
+    # open and read xml file
+    #with open(filename_xml, 'r') as xml_file:
+    #    xml_to_check = xml_file.read()
+
+    # parse xml
+    try:
+        doc = etree.parse(filename_xml)
+        #print(f'{filename_xml} XML well formed, syntax ok.')
+
+    # check for file IO error
+    except IOError:
+        #print('Invalid File')
+        post_error(f'{filename_xml}: IOError Invalid File')
+
+
+    # check for XML syntax errors
+    except etree.XMLSyntaxError as err:
+        #print('XML Syntax Error, see error_syntax.log')
+        post_error(f'{filename_xml}: {str(err.error_log)}: XMLSyntaxError Invalid File')
+
+    # check for general XML errors
+    except etree.LxmlError as err:
+        #print('XML Error, see error_syntax.log')
+        post_error(f'{filename_xml}: {str(err.error_log)}: LxmlError Invalid File')
+
+    except:
+        #print('Unknown error.')
+        post_error(f'{filename_xml}: Unknown error. Maybe check that no xml version is in the first line.')
+
+def parse_xml_files_from_APIs_dir():
+
+    for file in os.listdir("PowerEditor/installer/APIs"):
+        if file.endswith(".xml"):
+            #print(os.path.join("PowerEditor/installer/APIs", file))
+            parse_xml_file(os.path.join("PowerEditor/installer/APIs", file))
+
+def parse_xml_files_from_functionList_dir():
+
+    for file in os.listdir("PowerEditor/installer/functionList"):
+        if file.endswith(".xml"):
+            #print(os.path.join("PowerEditor/installer/functionList", file))
+            parse_xml_file(os.path.join("PowerEditor/installer/functionList", file))
+
+def parse_xml_files_from_nativeLang_dir():
+
+    for file in os.listdir("PowerEditor/installer/nativeLang"):
+        if file.endswith(".xml"):
+            #print(os.path.join("PowerEditor/installer/nativeLang", file))
+            parse_xml_file(os.path.join("PowerEditor/installer/nativeLang", file))
+
+def parse_xml_files_from_themes_dir():
+
+    for file in os.listdir("PowerEditor/installer/themes"):
+        if file.endswith(".xml"):
+            #print(os.path.join("PowerEditor/installer/themes", file))
+            parse_xml_file(os.path.join("PowerEditor/installer/themes", file))
+
+def parse_xml_files_from_src_dir():
+
+    for file in os.listdir("PowerEditor/src"):
+        if file.endswith(".xml"):
+            #print(os.path.join("PowerEditor/src", file))
+            parse_xml_file(os.path.join("PowerEditor/src", file))
+
+print('Start syntax check for xml files.')
+parse_xml_files_from_APIs_dir()
+parse_xml_files_from_functionList_dir()
+parse_xml_files_from_nativeLang_dir()
+parse_xml_files_from_themes_dir()
+parse_xml_files_from_src_dir()
+print('Done.')
+
+if has_error:
+    sys.exit(-2)
+else:
+    sys.exit()