basic lexer for Isabelle/HOL theorem prover

1 files changed, 217 insertions, 2 deletions

diff --git a/pygments/lexers/functional.py b/pygments/lexers/functional.py
index a22c4f55..d39dda2e 100644
--- a/pygments/lexers/functional.py
+++ b/pygments/lexers/functional.py
@@ -20,8 +20,8 @@ __all__ = ['RacketLexer', 'SchemeLexer', 'CommonLispLexer', 'CryptolLexer',
            'HaskellLexer', 'AgdaLexer', 'LiterateCryptolLexer',
            'LiterateHaskellLexer', 'LiterateAgdaLexer', 'SMLLexer',
            'OcamlLexer', 'ErlangLexer', 'ErlangShellLexer', 'OpaLexer',
-           'CoqLexer', 'NewLispLexer', 'NixLexer', 'ElixirLexer',
-           'ElixirConsoleLexer', 'KokaLexer', 'IdrisLexer',
+           'CoqLexer', 'IsabelleLexer', 'NewLispLexer', 'NixLexer',
+           'ElixirLexer', 'ElixirConsoleLexer', 'KokaLexer', 'IdrisLexer',
            'LiterateIdrisLexer']
 
 
@@ -2734,6 +2734,221 @@ class OpaLexer(RegexLexer):
         ],
     }
 
+class IsabelleLexer(RegexLexer):
+    """
+    For the `Isabelle <http://isabelle.in.tum.de/>`_ proof assistant.
+
+    .. versionadded:: 2.0
+    """
+
+    name = 'Isabelle'
+    aliases = ['isabelle']
+    filenames = ['*.thy']
+    mimetypes = ['text/x-isabelle']
+
+    keyword_minor = [
+        'and', 'assumes', 'attach', 'avoids', 'binder', 'checking',
+        'class_instance', 'class_relation', 'code_module', 'congs',
+        'constant', 'constrains', 'datatypes', 'defines', 'file', 'fixes',
+        'for', 'functions', 'hints', 'identifier', 'if', 'imports', 'in',
+        'includes', 'infix', 'infixl', 'infixr', 'is', 'keywords', 'lazy',
+        'module_name', 'monos', 'morphisms', 'no_discs_sels', 'notes',
+        'obtains', 'open', 'output', 'overloaded', 'parametric', 'permissive',
+        'pervasive', 'rep_compat', 'shows', 'structure', 'type_class',
+        'type_constructor', 'unchecked', 'unsafe', 'where',
+    ]
+
+    keyword_diag = [
+        'ML_command', 'ML_val', 'class_deps', 'code_deps', 'code_thms',
+        'display_drafts', 'find_consts', 'find_theorems', 'find_unused_assms',
+        'full_prf', 'help', 'locale_deps', 'nitpick', 'pr', 'prf',
+        'print_abbrevs', 'print_antiquotations', 'print_attributes',
+        'print_binds', 'print_bnfs', 'print_bundles',
+        'print_case_translations', 'print_cases', 'print_claset',
+        'print_classes', 'print_codeproc', 'print_codesetup',
+        'print_coercions', 'print_commands', 'print_context',
+        'print_defn_rules', 'print_dependencies', 'print_facts',
+        'print_induct_rules', 'print_inductives', 'print_interps',
+        'print_locale', 'print_locales', 'print_methods', 'print_options',
+        'print_orders', 'print_quot_maps', 'print_quotconsts',
+        'print_quotients', 'print_quotientsQ3', 'print_quotmapsQ3',
+        'print_rules', 'print_simpset', 'print_state', 'print_statement',
+        'print_syntax', 'print_theorems', 'print_theory', 'print_trans_rules',
+        'prop', 'pwd', 'quickcheck', 'refute', 'sledgehammer', 'smt_status',
+        'solve_direct', 'spark_status', 'term', 'thm', 'thm_deps', 'thy_deps',
+        'try', 'try0', 'typ', 'unused_thms', 'value', 'values', 'welcome',
+        'print_ML_antiquotations', 'print_term_bindings', 'values_prolog', 
+    ]
+
+    keyword_thy = [ 'theory', 'begin', 'end', ]
+
+    keyword_section = [ 'header', 'chapter', ]
+
+    keyword_subsection = [
+        'section', 'subsection', 'subsubsection', 'sect', 'subsect',
+        'subsubsect',
+    ]
+
+    keyword_theory_decl = [
+        'ML', 'ML_file', 'abbreviation', 'adhoc_overloading', 'arities',
+        'atom_decl', 'attribute_setup', 'axiomatization', 'bundle',
+        'case_of_simps', 'class', 'classes', 'classrel', 'codatatype',
+        'code_abort', 'code_class', 'code_const', 'code_datatype',
+        'code_identifier', 'code_include', 'code_instance', 'code_modulename',
+        'code_monad', 'code_printing', 'code_reflect', 'code_reserved',
+        'code_type', 'coinductive', 'coinductive_set', 'consts', 'context',
+        'datatype', 'datatype_new', 'datatype_new_compat', 'declaration',
+        'declare', 'default_sort', 'defer_recdef', 'definition', 'defs',
+        'domain', 'domain_isomorphism', 'domaindef', 'equivariance',
+        'export_code', 'extract', 'extract_type', 'fixrec', 'fun',
+        'fun_cases', 'hide_class', 'hide_const', 'hide_fact', 'hide_type',
+        'import_const_map', 'import_file', 'import_tptp', 'import_type_map',
+        'inductive', 'inductive_set', 'instantiation', 'judgment', 'lemmas',
+        'lifting_forget', 'lifting_update', 'local_setup', 'locale',
+        'method_setup', 'nitpick_params', 'no_adhoc_overloading',
+        'no_notation', 'no_syntax', 'no_translations', 'no_type_notation',
+        'nominal_datatype', 'nonterminal', 'notation', 'notepad', 'oracle',
+        'overloading', 'parse_ast_translation', 'parse_translation',
+        'partial_function', 'primcorec', 'primrec', 'primrec_new',
+        'print_ast_translation', 'print_translation', 'quickcheck_generator',
+        'quickcheck_params', 'realizability', 'realizers', 'recdef', 'record',
+        'refute_params', 'setup', 'setup_lifting', 'simproc_setup',
+        'simps_of_case', 'sledgehammer_params', 'spark_end', 'spark_open',
+        'spark_open_siv', 'spark_open_vcg', 'spark_proof_functions',
+        'spark_types', 'statespace', 'syntax', 'syntax_declaration', 'text',
+        'text_raw', 'theorems', 'translations', 'type_notation',
+        'type_synonym', 'typed_print_translation', 'typedecl', 'hoarestate',
+        'install_C_file', 'install_C_types', 'wpc_setup', 'c_defs', 'c_types',
+        'memsafe', 'SML_export', 'SML_file', 'SML_import', 'approximate',
+        'bnf_axiomatization', 'cartouche', 'datatype_compat',
+        'free_constructors', 'functor', 'nominal_function',
+        'nominal_termination', 'permanent_interpretation',
+        'binds', 'defining', 'smt2_status', 'term_cartouche',
+        'boogie_file', 'datatype_compat', 'text_cartouche',
+    ]
+
+    keyword_theory_script = ['inductive_cases', 'inductive_simps', ]
+
+    keyword_theory_goal = [
+        'ax_specification', 'bnf', 'code_pred', 'corollary', 'cpodef',
+        'crunch', 'crunch_ignore', 
+        'enriched_type', 'function', 'instance', 'interpretation', 'lemma',
+        'lift_definition', 'nominal_inductive', 'nominal_inductive2',
+        'nominal_primrec', 'pcpodef', 'primcorecursive',
+        'quotient_definition', 'quotient_type', 'recdef_tc', 'rep_datatype',
+        'schematic_corollary', 'schematic_lemma', 'schematic_theorem',
+        'spark_vc', 'specification', 'subclass', 'sublocale', 'termination',
+        'theorem', 'typedef', 'wrap_free_constructors',
+    ]
+    
+    keyword_qed = [ 'by', 'done', 'qed' ]
+    keyword_abandon_proof = ['sorry', 'oops']
+
+    keyword_proof_goal = ['have', 'hence', 'interpret', ]
+
+    keyword_proof_block = [ 'next', 'proof', ]
+
+    keyword_proof_chain = [
+        'finally', 'from', 'then', 'ultimately', 'with',
+    ]
+
+    keyword_proof_decl = [
+        'ML_prf', 'also', 'include', 'including', 'let', 'moreover', 'note',
+        'txt', 'txt_raw', 'unfolding', 'using', 'write',
+    ]
+
+    keyword_proof_asm = [ 'assume', 'case', 'def', 'fix', 'presume', ]
+
+    keyword_proof_asm_goal = [ 'guess', 'obtain', 'show', 'thus', ]
+
+    keyword_proof_script = [
+        'apply', 'apply_end', 'apply_trace', 'back', 'defer', 'prefer',
+    ]
+
+    operators = [
+        '\\:\\:', '\\:', '\\(', '\\)', '\\[', '\\]', '_', '=', ',', '\\|',
+        '\\+', '\\-', '\\!', '\\?',
+	]
+
+    proof_operators = [ '\\{', '\\}', '\\.', '\\.\\.', ]
+
+    tokens = {
+        'root': [
+            (r'\s+', Text),
+            (r'\(\*', Comment, 'comment'),
+            (r'\{\*', Comment, 'text'),
+
+			(r'(%s)' % '|'.join(operators), Operator),
+			(r'(%s)' % '|'.join(proof_operators), Operator.Word),
+
+            (r'\b(%s)\b' % '|'.join(keyword_minor), Keyword.Pseudo),
+
+            (r'\b(%s)\b' % '|'.join(keyword_diag), Keyword.Type),
+
+            (r'\b(%s)\b' % '|'.join(keyword_thy), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_theory_decl), Keyword),
+
+            (r'\b(%s)\b' % '|'.join(keyword_section), Generic.Heading),
+            (r'\b(%s)\b' % '|'.join(keyword_subsection), Generic.Subheading),
+
+            (r'\b(%s)\b' % '|'.join(keyword_theory_goal), Keyword.Namespace),
+            (r'\b(%s)\b' % '|'.join(keyword_theory_script), Keyword.Namespace),
+
+            (r'\b(%s)\b' % '|'.join(keyword_abandon_proof), Generic.Error),
+
+            (r'\b(%s)\b' % '|'.join(keyword_qed), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_proof_goal), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_proof_block), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_proof_decl), Keyword),
+
+            (r'\b(%s)\b' % '|'.join(keyword_proof_chain), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_proof_asm), Keyword),
+            (r'\b(%s)\b' % '|'.join(keyword_proof_asm_goal), Keyword),
+
+            (r'\b(%s)\b' % '|'.join(keyword_proof_script), Keyword.Pseudo),
+
+            (r'\\<\w*>', Text.Symbol),
+
+            (r"[^\W\d][.\w']*", Name),
+            (r"\?[^\W\d][.\w']*", Name),
+            (r"'[^\W\d][.\w']*", Name.Type),
+
+            (r'\d[\d_]*', Name), # display numbers as name
+            (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
+            (r'0[oO][0-7][0-7_]*', Number.Oct),
+            (r'0[bB][01][01_]*', Number.Bin),
+
+            (r'"', String, 'string'),
+            (r'`', String.Other, 'fact'),
+        ],
+        'comment': [
+            (r'[^(*)]+', Comment),
+            (r'\(\*', Comment, '#push'),
+            (r'\*\)', Comment, '#pop'),
+            (r'[(*)]', Comment),
+        ],
+        'text': [
+            (r'[^\*\}]+', Comment),
+            (r'\*\}', Comment, '#pop'),
+            (r'\*', Comment),
+            (r'\}', Comment),
+        ],
+        'string': [
+            (r'[^"\\]+', String),
+			(r'\\<\w*>', String.Symbol),
+            (r'\\"', String),
+            (r'\\', String),
+            (r'"', String, '#pop'),
+        ],
+        'fact': [
+            (r'[^`\\]+', String.Other),
+			(r'\\<\w*>', String.Symbol),
+            (r'\\`', String.Other),
+            (r'\\', String.Other),
+            (r'`', String.Other, '#pop'),
+        ],
+    }
+
 
 class CoqLexer(RegexLexer):
     """