Integrate heuristics into lexer selection

README.md

@@ -29,7 +29,7 @@ This only covers the RegexLexers, which are the most common ones,
 but it means the supported languages are a subset of Chroma's, which
 is a subset of Pygments'.
 
-Currently Tartrazine supports ... 247 languages.
+Currently Tartrazine supports ... 248 languages.
 
 It has 331 themes (63 from Chroma, the rest are base16 themes via
 [Sixteen](https://github.com/ralsina/sixteen)

scripts/lexer_metadata.py

@@ -52,6 +52,6 @@ with open("src/constants/lexers.cr", "w") as f:
     f.write("  LEXERS_BY_FILENAME = {\n")
     for k in sorted(lexer_by_filename.keys()):
         v = lexer_by_filename[k]
-        f.write(f'"{k}" => {str(sorted(list(v))).replace("'", "\"")}, \n')
+        f.write(f'"{k}" => {str(list(v)).replace("'", "\"")}, \n')
     f.write("}\n")
     f.write("end\n")

shard.yml

@@ -1,5 +1,5 @@
 name: tartrazine
-version: 0.6.1
+version: 0.6.0
 
 authors:
   - Roberto Alsina <roberto.alsina@gmail.com>

src/constants/lexers.cr

@@ -731,8 +731,8 @@ module Tartrazine
     "*.applescript"     => ["applescript"],
     "*.aql"             => ["arangodb_aql"],
     "*.arexx"           => ["rexx"],
-    "*.as"              => ["actionscript", "actionscript_3"],
+    "*.as"              => ["actionscript_3", "actionscript"],
-    "*.asm"             => ["nasm", "tasm", "z80_assembly"],
+    "*.asm"             => ["nasm", "z80_assembly", "tasm"],
     "*.au3"             => ["autoit"],
     "*.automount"       => ["systemd"],
     "*.aux"             => ["tex"],
@@ -740,7 +740,7 @@ module Tartrazine
     "*.awk"             => ["awk"],
     "*.b"               => ["brainfuck"],
     "*.bal"             => ["ballerina"],
-    "*.bas"             => ["qbasic", "vb_net"],
+    "*.bas"             => ["vb_net", "qbasic"],
     "*.bash"            => ["bash"],
     "*.bat"             => ["batchfile"],
     "*.batch"           => ["psl"],
@@ -850,7 +850,7 @@ module Tartrazine
     "*.graphql"         => ["graphql"],
     "*.graphqls"        => ["graphql"],
     "*.groovy"          => ["groovy"],
-    "*.h"               => ["c", "c++", "objective-c"],
+    "*.h"               => ["objective-c", "c", "c++"],
     "*.h++"             => ["c++"],
     "*.ha"              => ["hare"],
     "*.handlebars"      => ["handlebars"],
@@ -873,7 +873,7 @@ module Tartrazine
     "*.idc"             => ["c"],
     "*.idr"             => ["idris"],
     "*.ijs"             => ["j"],
-    "*.inc"             => ["objectpascal", "php", "povray", "sourcepawn"],
+    "*.inc"             => ["php", "objectpascal", "povray", "sourcepawn"],
     "*.inf"             => ["ini"],
     "*.ini"             => ["ini"],
     "*.ino"             => ["arduino"],
@@ -899,7 +899,7 @@ module Tartrazine
     "*.lpk"             => ["objectpascal"],
     "*.lpr"             => ["objectpascal"],
     "*.lua"             => ["lua"],
-    "*.m"               => ["mason", "mathematica", "matlab", "objective-c", "octave"],
+    "*.m"               => ["mathematica", "mason", "octave", "objective-c", "matlab"],
     "*.ma"              => ["mathematica"],
     "*.mak"             => ["makefile"],
     "*.man"             => ["groff"],
@@ -954,7 +954,7 @@ module Tartrazine
     "*.php"             => ["php"],
     "*.php[345]"        => ["php"],
     "*.pig"             => ["pig"],
-    "*.pl"              => ["perl", "prolog"],
+    "*.pl"              => ["prolog", "perl"],
     "*.plc"             => ["plutus_core"],
     "*.plot"            => ["gnuplot"],
     "*.plt"             => ["gnuplot"],
@@ -962,7 +962,7 @@ module Tartrazine
     "*.pml"             => ["promela"],
     "*.pony"            => ["pony"],
     "*.pov"             => ["povray"],
-    "*.pp"              => ["objectpascal", "puppet"],
+    "*.pp"              => ["puppet", "objectpascal"],
     "*.pq"              => ["powerquery"],
     "*.pr"              => ["promela"],
     "*.prm"             => ["promela"],
@@ -1011,7 +1011,7 @@ module Tartrazine
     "*.rst"             => ["rst"],
     "*.rvt"             => ["tcl"],
     "*.rx"              => ["rexx"],
-    "*.s"               => ["armasm", "gas", "r"],
+    "*.s"               => ["armasm", "r", "gas"],
     "*.sage"            => ["python"],
     "*.sas"             => ["sas"],
     "*.sass"            => ["sass"],
@@ -1024,7 +1024,7 @@ module Tartrazine
     "*.scope"           => ["systemd"],
     "*.scss"            => ["scss"],
     "*.sed"             => ["sed"],
-    "*.service"         => ["ini", "systemd"],
+    "*.service"         => ["systemd", "ini"],
     "*.sh"              => ["bash"],
     "*.sh-session"      => ["bash_session"],
     "*.sieve"           => ["sieve"],
@@ -1034,13 +1034,13 @@ module Tartrazine
     "*.smali"           => ["smali"],
     "*.sml"             => ["standard_ml"],
     "*.snobol"          => ["snobol"],
-    "*.socket"          => ["ini", "systemd"],
+    "*.socket"          => ["systemd", "ini"],
     "*.sol"             => ["solidity"],
     "*.sp"              => ["sourcepawn"],
     "*.sparql"          => ["sparql"],
     "*.spec"            => ["rpm_spec"],
     "*.spt"             => ["cheetah"],
-    "*.sql"             => ["mysql", "sql"],
+    "*.sql"             => ["sql", "mysql"],
     "*.ss"              => ["scheme"],
     "*.st"              => ["smalltalk"],
     "*.stas"            => ["stas"],
@@ -1069,7 +1069,7 @@ module Tartrazine
     "*.tpl"             => ["smarty"],
     "*.tpp"             => ["c++"],
     "*.trig"            => ["psl"],
-    "*.ts"              => ["typescript", "typoscript"],
+    "*.ts"              => ["typoscript", "typescript"],
     "*.tst"             => ["scilab"],
     "*.tsx"             => ["typescript"],
     "*.ttl"             => ["turtle"],
@@ -1079,7 +1079,7 @@ module Tartrazine
     "*.twig"            => ["twig"],
     "*.txt"             => ["plaintext"],
     "*.uc"              => ["ucode"],
-    "*.v"               => ["coq", "v", "verilog"],
+    "*.v"               => ["verilog", "v", "coq"],
     "*.vala"            => ["vala"],
     "*.vapi"            => ["vala"],
     "*.vb"              => ["vb_net"],