Merge pull request #2588 from jeanas/urls

Add URLs to lexers and require the `url` attribute

pygments/lexer.py

@@ -130,7 +130,7 @@ class Lexer(metaclass=LexerMeta):
     priority = 0
 
     #: URL of the language specification/definition. Used in the Pygments
-    #: documentation.
+    #: documentation. Set to an empty string to disable.
     url = None
 
     #: Example file name. Relative to the ``tests/examplefiles`` directory.

pygments/lexers/actionscript.py

@@ -29,6 +29,7 @@ class ActionScriptLexer(RegexLexer):
     filenames = ['*.as']
     mimetypes = ['application/x-actionscript', 'text/x-actionscript',
                  'text/actionscript']
+    url = 'https://en.wikipedia.org/wiki/ActionScript'
 
     flags = re.DOTALL
     tokens = {
@@ -213,6 +214,7 @@ class MxmlLexer(RegexLexer):
     aliases = ['mxml']
     filenames = ['*.mxml']
     mimetimes = ['text/xml', 'application/xml']
+    url = 'https://en.wikipedia.org/wiki/MXML'
 
     tokens = {
         'root': [

pygments/lexers/ada.py

@@ -30,6 +30,7 @@ class AdaLexer(RegexLexer):
     aliases = ['ada', 'ada95', 'ada2005']
     filenames = ['*.adb', '*.ads', '*.ada']
     mimetypes = ['text/x-ada']
+    url = 'https://www.adaic.org'
 
     flags = re.MULTILINE | re.IGNORECASE
 

pygments/lexers/algebra.py

@@ -98,6 +98,7 @@ class GAPConsoleLexer(Lexer):
     name = 'GAP session'
     aliases = ['gap-console', 'gap-repl']
     filenames = ['*.tst']
+    url = 'https://www.gap-system.org'
 
     def get_tokens_unprocessed(self, text):
         gaplexer = GAPLexer(**self.options)

pygments/lexers/amdgpu.py

@@ -25,6 +25,7 @@ class AMDGPULexer(RegexLexer):
     name = 'AMDGPU'
     aliases = ['amdgpu']
     filenames = ['*.isa']
+    url = 'https://gpuopen.com/amd-isa-documentation'
 
     flags = re.IGNORECASE
 

pygments/lexers/apdlexer.py

@@ -26,6 +26,8 @@ class apdlexer(RegexLexer):
     name = 'ANSYS parametric design language'
     aliases = ['ansys', 'apdl']
     filenames = ['*.ans']
+    url = 'https://www.ansys.com'
+
     flags = re.IGNORECASE
 
     # list of elements

pygments/lexers/archetype.py

@@ -2,11 +2,7 @@
     pygments.lexers.archetype
     ~~~~~~~~~~~~~~~~~~~~~~~~~
 
-    Lexer for Archetype-related syntaxes, including:
-
-    - ODIN syntax <https://github.com/openEHR/odin>
-    - ADL syntax <http://www.openehr.org/releases/trunk/architecture/am/adl2.pdf>
-    - cADL sub-syntax of ADL
+    Lexer for Archetype-related syntaxes, including ODIN, ADL and cADL.
 
     For uses of this syntax, see the openEHR archetypes <http://www.openEHR.org/ckm>
 
@@ -146,6 +142,7 @@ class OdinLexer(AtomsLexer):
     aliases = ['odin']
     filenames = ['*.odin']
     mimetypes = ['text/odin']
+    url = 'https://github.com/openEHR/odin'
 
     tokens = {
         'path': [
@@ -194,6 +191,7 @@ class CadlLexer(AtomsLexer):
     name = 'cADL'
     aliases = ['cadl']
     filenames = ['*.cadl']
+    url = 'https://specifications.openehr.org/releases/AM/latest/ADL2.html#_cadl_constraint_adl'
 
     tokens = {
         'path': [
@@ -260,6 +258,7 @@ class AdlLexer(AtomsLexer):
     name = 'ADL'
     aliases = ['adl']
     filenames = ['*.adl', '*.adls', '*.adlf', '*.adlx']
+    url = 'https://specifications.openehr.org/releases/AM/latest/ADL2.html'
 
     tokens = {
         'whitespace': [

pygments/lexers/asc.py

@@ -32,6 +32,7 @@ class AscLexer(RegexLexer):
     ]
     mimetypes = ['application/pgp-keys', 'application/pgp-encrypted',
                  'application/pgp-signature', 'application/pem-certificate-chain']
+    url = 'https://www.openpgp.org'
 
     flags = re.MULTILINE
 

pygments/lexers/asm.py

@@ -31,6 +31,7 @@ class GasLexer(RegexLexer):
     aliases = ['gas', 'asm']
     filenames = ['*.s', '*.S']
     mimetypes = ['text/x-gas']
+    url = 'https://www.gnu.org/software/binutils'
 
     #: optional Comment or Whitespace
     string = r'"(\\"|[^"])*"'
@@ -167,6 +168,7 @@ class ObjdumpLexer(RegexLexer):
     aliases = ['objdump']
     filenames = ['*.objdump']
     mimetypes = ['text/x-objdump']
+    url = 'https://www.gnu.org/software/binutils'
 
     tokens = _objdump_lexer_tokens(GasLexer)
 
@@ -179,6 +181,7 @@ class DObjdumpLexer(DelegatingLexer):
     aliases = ['d-objdump']
     filenames = ['*.d-objdump']
     mimetypes = ['text/x-d-objdump']
+    url = 'https://www.gnu.org/software/binutils'
 
     def __init__(self, **options):
         super().__init__(DLexer, ObjdumpLexer, **options)
@@ -192,6 +195,7 @@ class CppObjdumpLexer(DelegatingLexer):
     aliases = ['cpp-objdump', 'c++-objdumb', 'cxx-objdump']
     filenames = ['*.cpp-objdump', '*.c++-objdump', '*.cxx-objdump']
     mimetypes = ['text/x-cpp-objdump']
+    url = 'https://www.gnu.org/software/binutils'
 
     def __init__(self, **options):
         super().__init__(CppLexer, ObjdumpLexer, **options)
@@ -205,6 +209,8 @@ class CObjdumpLexer(DelegatingLexer):
     aliases = ['c-objdump']
     filenames = ['*.c-objdump']
     mimetypes = ['text/x-c-objdump']
+    url = 'https://www.gnu.org/software/binutils'
+
 
     def __init__(self, **options):
         super().__init__(CLexer, ObjdumpLexer, **options)
@@ -220,6 +226,7 @@ class HsailLexer(RegexLexer):
     aliases = ['hsail', 'hsa']
     filenames = ['*.hsail']
     mimetypes = ['text/x-hsail']
+    url = 'https://en.wikipedia.org/wiki/Heterogeneous_System_Architecture#HSA_Intermediate_Layer'
 
     string = r'"[^"]*?"'
     identifier = r'[a-zA-Z_][\w.]*'
@@ -715,6 +722,7 @@ class NasmLexer(RegexLexer):
     aliases = ['nasm']
     filenames = ['*.asm', '*.ASM', '*.nasm']
     mimetypes = ['text/x-nasm']
+    url = 'https://nasm.us'
 
     # Tasm uses the same file endings, but TASM is not as common as NASM, so
     # we prioritize NASM higher by default
@@ -803,6 +811,7 @@ class NasmObjdumpLexer(ObjdumpLexer):
     aliases = ['objdump-nasm']
     filenames = ['*.objdump-intel']
     mimetypes = ['text/x-nasm-objdump']
+    url = 'https://www.gnu.org/software/binutils'
 
     tokens = _objdump_lexer_tokens(NasmLexer)
 
@@ -815,6 +824,7 @@ class TasmLexer(RegexLexer):
     aliases = ['tasm']
     filenames = ['*.asm', '*.ASM', '*.tasm']
     mimetypes = ['text/x-tasm']
+    url = 'https://en.wikipedia.org/wiki/Turbo_Assembler'
 
     identifier = r'[@a-z$._?][\w$.?#@~]*'
     hexn = r'(?:0x[0-9a-f]+|$0[0-9a-f]*|[0-9]+[0-9a-f]*h)'
@@ -902,6 +912,7 @@ class Ca65Lexer(RegexLexer):
     name = 'ca65 assembler'
     aliases = ['ca65']
     filenames = ['*.s']
+    url = 'https://cc65.github.io'
 
     flags = re.IGNORECASE
 

pygments/lexers/basic.py

@@ -194,9 +194,7 @@ class BlitzBasicLexer(RegexLexer):
 
 class MonkeyLexer(RegexLexer):
     """
-    For
-    `Monkey <https://en.wikipedia.org/wiki/Monkey_(programming_language)>`_
-    source code.
+    For Monkey source code.
 
     .. versionadded:: 1.6
     """
@@ -205,6 +203,7 @@ class MonkeyLexer(RegexLexer):
     aliases = ['monkey']
     filenames = ['*.monkey']
     mimetypes = ['text/x-monkey']
+    url = 'https://blitzresearch.itch.io/monkeyx'
 
     name_variable = r'[a-z_]\w*'
     name_function = r'[A-Z]\w*'
@@ -331,6 +330,7 @@ class CbmBasicV2Lexer(RegexLexer):
     name = 'CBM BASIC V2'
     aliases = ['cbmbas']
     filenames = ['*.bas']
+    url = 'https://en.wikipedia.org/wiki/Commodore_BASIC'
 
     flags = re.IGNORECASE
 
@@ -362,9 +362,7 @@ def analyse_text(text):
 
 class QBasicLexer(RegexLexer):
     """
-    For
-    `QBasic <http://en.wikipedia.org/wiki/QBasic>`_
-    source code.
+    For QBasic source code.
 
     .. versionadded:: 2.0
     """
@@ -373,6 +371,7 @@ class QBasicLexer(RegexLexer):
     aliases = ['qbasic', 'basic']
     filenames = ['*.BAS', '*.bas']
     mimetypes = ['text/basic']
+    url = 'https://en.wikipedia.org/wiki/QBasic'
 
     declarations = ('DATA', 'LET')
 
@@ -512,6 +511,8 @@ class VBScriptLexer(RegexLexer):
     name = 'VBScript'
     aliases = ['vbscript']
     filenames = ['*.vbs', '*.VBS']
+    url = 'https://learn.microsoft.com/en-us/previous-versions/t0aew7h6(v=vs.85)'
+
     flags = re.IGNORECASE
 
     tokens = {
@@ -607,6 +608,7 @@ class BBCBasicLexer(RegexLexer):
     name = 'BBC Basic'
     aliases = ['bbcbasic']
     filenames = ['*.bbc']
+    url = 'https://www.bbcbasic.co.uk/bbcbasic.html'
 
     tokens = {
         'root': [

pygments/lexers/bdd.py

@@ -3,7 +3,6 @@
     ~~~~~~~~~~~~~~~~~~~
 
     Lexer for BDD(Behavior-driven development).
-    More information: https://en.wikipedia.org/wiki/Behavior-driven_development
 
     :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
@@ -27,6 +26,7 @@ class BddLexer(RegexLexer):
     aliases = ['bdd']
     filenames = ['*.feature']
     mimetypes = ['text/x-bdd']
+    url = 'https://en.wikipedia.org/wiki/Behavior-driven_development'
 
     step_keywords = (r'Given|When|Then|Add|And|Feature|Scenario Outline|'
                      r'Scenario|Background|Examples|But')

pygments/lexers/berry.py

@@ -17,14 +17,15 @@
 
 class BerryLexer(RegexLexer):
     """
-    For `berry <http://github.com/berry-lang/berry>`_ source code.
+    For Berry source code.
 
     .. versionadded:: 2.12.0
     """
     name = 'Berry'
     aliases = ['berry', 'be']
     filenames = ['*.be']
     mimetypes = ['text/x-berry', 'application/x-berry']
+    url = 'https://berry-lang.github.io'
 
     _name = r'\b[^\W\d]\w*'
 

pygments/lexers/bibtex.py

@@ -30,6 +30,7 @@ class BibTeXLexer(ExtendedRegexLexer):
     filenames = ['*.bib']
     mimetypes = ["text/x-bibtex"]
     flags = re.IGNORECASE
+    url = 'https://texfaq.org/FAQ-BibTeXing'
 
     ALLOWED_CHARS = r'@!$&*+\-./:;<>?\[\\\]^`|~'
     IDENTIFIER = '[{}][{}]*'.format('a-z_' + ALLOWED_CHARS, r'\w' + ALLOWED_CHARS)
@@ -124,6 +125,7 @@ class BSTLexer(RegexLexer):
     aliases = ['bst', 'bst-pybtex']
     filenames = ['*.bst']
     flags = re.IGNORECASE | re.MULTILINE
+    url = 'https://texfaq.org/FAQ-BibTeXing'
 
     tokens = {
         'root': [

pygments/lexers/boa.py

@@ -17,13 +17,14 @@
 
 class BoaLexer(RegexLexer):
     """
-    Lexer for the `Boa <http://boa.cs.iastate.edu/docs/>`_ language.
+    Lexer for the Boa language.
 
     .. versionadded:: 2.4
     """
     name = 'Boa'
     aliases = ['boa']
     filenames = ['*.boa']
+    url = 'https://boa.cs.iastate.edu/docs'
 
     reserved = words(
         ('input', 'output', 'of', 'weight', 'before', 'after', 'stop',

pygments/lexers/business.py

@@ -30,6 +30,8 @@ class CobolLexer(RegexLexer):
     aliases = ['cobol']
     filenames = ['*.cob', '*.COB', '*.cpy', '*.CPY']
     mimetypes = ['text/x-cobol']
+    url = 'https://en.wikipedia.org/wiki/COBOL'
+
     flags = re.IGNORECASE | re.MULTILINE
 
     # Data Types: by PICTURE and USAGE
@@ -228,6 +230,8 @@ class CobolFreeformatLexer(CobolLexer):
     aliases = ['cobolfree']
     filenames = ['*.cbl', '*.CBL']
     mimetypes = []
+    url = 'https://opencobol.add1tocobol.com'
+
     flags = re.IGNORECASE | re.MULTILINE
 
     tokens = {
@@ -247,6 +251,7 @@ class ABAPLexer(RegexLexer):
     aliases = ['abap']
     filenames = ['*.abap', '*.ABAP']
     mimetypes = ['text/x-abap']
+    url = 'https://community.sap.com/topics/abap'
 
     flags = re.IGNORECASE | re.MULTILINE
 
@@ -448,15 +453,15 @@ class ABAPLexer(RegexLexer):
 
 class OpenEdgeLexer(RegexLexer):
     """
-    Lexer for `OpenEdge ABL (formerly Progress)
-    <http://web.progress.com/en/openedge/abl.html>`_ source code.
+    Lexer for OpenEdge ABL (formerly Progress) source code.
 
     .. versionadded:: 1.5
     """
     name = 'OpenEdge ABL'
     aliases = ['openedge', 'abl', 'progress']
     filenames = ['*.p', '*.cls']
     mimetypes = ['text/x-openedge', 'application/x-openedge']
+    url = 'https://www.progress.com/openedge/features/abl'
 
     types = (r'(?i)(^|(?<=[^\w\-]))(CHARACTER|CHAR|CHARA|CHARAC|CHARACT|CHARACTE|'
              r'COM-HANDLE|DATE|DATETIME|DATETIME-TZ|'
@@ -517,10 +522,7 @@ def analyse_text(text):
 
 class GoodDataCLLexer(RegexLexer):
     """
-    Lexer for `GoodData-CL
-    <https://github.com/gooddata/GoodData-CL/raw/master/cli/src/main/resources/\
-com/gooddata/processor/COMMANDS.txt>`_
-    script files.
+    Lexer for GoodData-CL script files.
 
     .. versionadded:: 1.4
     """
@@ -529,8 +531,12 @@ class GoodDataCLLexer(RegexLexer):
     aliases = ['gooddata-cl']
     filenames = ['*.gdc']
     mimetypes = ['text/x-gooddata-cl']
+    url = 'https://github.com/gooddata/GoodData-CL'
 
     flags = re.IGNORECASE
+
+    # Syntax:
+    # https://github.com/gooddata/GoodData-CL/raw/master/cli/src/main/resources/com/gooddata/processor/COMMANDS.txt
     tokens = {
         'root': [
             # Comments
@@ -564,9 +570,7 @@ class GoodDataCLLexer(RegexLexer):
 
 class MaqlLexer(RegexLexer):
     """
-    Lexer for `GoodData MAQL
-    <https://secure.gooddata.com/docs/html/advanced.metric.tutorial.html>`_
-    scripts.
+    Lexer for GoodData MAQL scripts.
 
     .. versionadded:: 1.4
     """
@@ -575,6 +579,7 @@ class MaqlLexer(RegexLexer):
     aliases = ['maql']
     filenames = ['*.maql']
     mimetypes = ['text/x-gooddata-maql', 'application/x-gooddata-maql']
+    url = 'https://help.gooddata.com/doc/enterprise/en/dashboards-and-insights/maql-analytical-query-language'
 
     flags = re.IGNORECASE
     tokens = {