Split PHP into two lexers - PHP and PHTML.

The former is pure PHP code while the latter is PHP code in <? ?> tags,
within HTML.

Fixes #210.

.golangci.yml

@@ -20,6 +20,11 @@ linters:
     - wsl
     - gomnd
     - gocognit
+    - goerr113
+    - nolintlint
+    - testpackage
+    - godot
+    - nestif
 
 linters-settings:
   govet:

.travis.yml

@@ -4,7 +4,7 @@ go:
   - "1.13.x"
 script:
   - go test -v ./...
-  - curl -sfL https://install.goreleaser.com/github.com/golangci/golangci-lint.sh | bash -s v1.22.2
+  - curl -sfL https://install.goreleaser.com/github.com/golangci/golangci-lint.sh | bash -s 1.26.0
   - ./bin/golangci-lint run
   - git clean -fdx .
 after_success:

lexers/circular/php.go

@@ -1,15 +1,12 @@
 package circular
 
 import (
-	"strings"
-
 	. "github.com/alecthomas/chroma" // nolint
-	"github.com/alecthomas/chroma/lexers/h"
 	"github.com/alecthomas/chroma/lexers/internal"
 )
 
-// PHP lexer.
+// PHP lexer for pure PHP code (not embedded in HTML).
-var PHP = internal.Register(DelegatingLexer(h.HTML, MustNewLexer(
+var PHP = internal.Register(MustNewLexer(
 	&Config{
 		Name:            "PHP",
 		Aliases:         []string{"php", "php3", "php4", "php5"},
@@ -19,73 +16,65 @@ var PHP = internal.Register(DelegatingLexer(h.HTML, MustNewLexer(
 		CaseInsensitive: true,
 		EnsureNL:        true,
 	},
-	Rules{
+	phpCommonRules.Rename("php", "root"),
-		"root": {
+))
-			{`<\?(php)?`, CommentPreproc, Push("php")},
+
-			{`[^<]+`, Other, nil},
+var phpCommonRules = Rules{
-			{`<`, Other, nil},
+	"php": {
-		},
+		{`\?>`, CommentPreproc, Pop(1)},
-		"php": {
+		{`(<<<)([\'"]?)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)(\2\n.*?\n\s*)(\3)(;?)(\n)`, ByGroups(LiteralString, LiteralString, LiteralStringDelimiter, LiteralString, LiteralStringDelimiter, Punctuation, Text), nil},
-			{`\?>`, CommentPreproc, Pop(1)},
+		{`\s+`, Text, nil},
-			{`(<<<)([\'"]?)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)(\2\n.*?\n\s*)(\3)(;?)(\n)`, ByGroups(LiteralString, LiteralString, LiteralStringDelimiter, LiteralString, LiteralStringDelimiter, Punctuation, Text), nil},
+		{`#.*?\n`, CommentSingle, nil},
-			{`\s+`, Text, nil},
+		{`//.*?\n`, CommentSingle, nil},
-			{`#.*?\n`, CommentSingle, nil},
+		{`/\*\*/`, CommentMultiline, nil},
-			{`//.*?\n`, CommentSingle, nil},
+		{`/\*\*.*?\*/`, LiteralStringDoc, nil},
-			{`/\*\*/`, CommentMultiline, nil},
+		{`/\*.*?\*/`, CommentMultiline, nil},
-			{`/\*\*.*?\*/`, LiteralStringDoc, nil},
+		{`(->|::)(\s*)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)`, ByGroups(Operator, Text, NameAttribute), nil},
-			{`/\*.*?\*/`, CommentMultiline, nil},
+		{`[~!%^&*+=|:.<>/@-]+`, Operator, nil},
-			{`(->|::)(\s*)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)`, ByGroups(Operator, Text, NameAttribute), nil},
+		{`\?`, Operator, nil},
-			{`[~!%^&*+=|:.<>/@-]+`, Operator, nil},
+		{`[\[\]{}();,]+`, Punctuation, nil},
-			{`\?`, Operator, nil},
+		{`(class)(\s+)`, ByGroups(Keyword, Text), Push("classname")},
-			{`[\[\]{}();,]+`, Punctuation, nil},
+		{`(function)(\s*)(?=\()`, ByGroups(Keyword, Text), nil},
-			{`(class)(\s+)`, ByGroups(Keyword, Text), Push("classname")},
+		{`(function)(\s+)(&?)(\s*)`, ByGroups(Keyword, Text, Operator, Text), Push("functionname")},
-			{`(function)(\s*)(?=\()`, ByGroups(Keyword, Text), nil},
+		{`(const)(\s+)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)`, ByGroups(Keyword, Text, NameConstant), nil},
-			{`(function)(\s+)(&?)(\s*)`, ByGroups(Keyword, Text, Operator, Text), Push("functionname")},
+		{`(and|E_PARSE|old_function|E_ERROR|or|as|E_WARNING|parent|eval|PHP_OS|break|exit|case|extends|PHP_VERSION|cfunction|FALSE|print|for|require|continue|foreach|require_once|declare|return|default|static|do|switch|die|stdClass|echo|else|TRUE|elseif|var|empty|if|xor|enddeclare|include|virtual|endfor|include_once|while|endforeach|global|endif|list|endswitch|new|endwhile|not|array|E_ALL|NULL|final|php_user_filter|interface|implements|public|private|protected|abstract|clone|try|catch|throw|this|use|namespace|trait|yield|finally)\b`, Keyword, nil},
-			{`(const)(\s+)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)`, ByGroups(Keyword, Text, NameConstant), nil},
+		{`(true|false|null)\b`, KeywordConstant, nil},
-			{`(and|E_PARSE|old_function|E_ERROR|or|as|E_WARNING|parent|eval|PHP_OS|break|exit|case|extends|PHP_VERSION|cfunction|FALSE|print|for|require|continue|foreach|require_once|declare|return|default|static|do|switch|die|stdClass|echo|else|TRUE|elseif|var|empty|if|xor|enddeclare|include|virtual|endfor|include_once|while|endforeach|global|endif|list|endswitch|new|endwhile|not|array|E_ALL|NULL|final|php_user_filter|interface|implements|public|private|protected|abstract|clone|try|catch|throw|this|use|namespace|trait|yield|finally)\b`, Keyword, nil},
+		Include("magicconstants"),
-			{`(true|false|null)\b`, KeywordConstant, nil},
+		{`\$\{\$+(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*\}`, NameVariable, nil},
-			Include("magicconstants"),
+		{`\$+(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameVariable, nil},
-			{`\$\{\$+(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*\}`, NameVariable, nil},
+		{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameOther, nil},
-			{`\$+(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameVariable, nil},
+		{`(\d+\.\d*|\d*\.\d+)(e[+-]?[0-9]+)?`, LiteralNumberFloat, nil},
-			{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameOther, nil},
+		{`\d+e[+-]?[0-9]+`, LiteralNumberFloat, nil},
-			{`(\d+\.\d*|\d*\.\d+)(e[+-]?[0-9]+)?`, LiteralNumberFloat, nil},
+		{`0[0-7]+`, LiteralNumberOct, nil},
-			{`\d+e[+-]?[0-9]+`, LiteralNumberFloat, nil},
+		{`0x[a-f0-9]+`, LiteralNumberHex, nil},
-			{`0[0-7]+`, LiteralNumberOct, nil},
+		{`\d+`, LiteralNumberInteger, nil},
-			{`0x[a-f0-9]+`, LiteralNumberHex, nil},
+		{`0b[01]+`, LiteralNumberBin, nil},
-			{`\d+`, LiteralNumberInteger, nil},
+		{`'([^'\\]*(?:\\.[^'\\]*)*)'`, LiteralStringSingle, nil},
-			{`0b[01]+`, LiteralNumberBin, nil},
+		{"`([^`\\\\]*(?:\\\\.[^`\\\\]*)*)`", LiteralStringBacktick, nil},
-			{`'([^'\\]*(?:\\.[^'\\]*)*)'`, LiteralStringSingle, nil},
+		{`"`, LiteralStringDouble, Push("string")},
-			{"`([^`\\\\]*(?:\\\\.[^`\\\\]*)*)`", LiteralStringBacktick, nil},
-			{`"`, LiteralStringDouble, Push("string")},
-		},
-		"magicfuncs": {
-			{Words(``, `\b`, `__construct`, `__destruct`, `__call`, `__callStatic`, `__get`, `__set`, `__isset`, `__unset`, `__sleep`, `__wakeup`, `__toString`, `__invoke`, `__set_state`, `__clone`, `__debugInfo`), NameFunctionMagic, nil},
-		},
-		"magicconstants": {
-			{Words(``, `\b`, `__LINE__`, `__FILE__`, `__DIR__`, `__FUNCTION__`, `__CLASS__`, `__TRAIT__`, `__METHOD__`, `__NAMESPACE__`), NameConstant, nil},
-		},
-		"classname": {
-			{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameClass, Pop(1)},
-		},
-		"functionname": {
-			Include("magicfuncs"),
-			{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameFunction, Pop(1)},
-			Default(Pop(1)),
-		},
-		"string": {
-			{`"`, LiteralStringDouble, Pop(1)},
-			{`[^{$"\\]+`, LiteralStringDouble, nil},
-			{`\\([nrt"$\\]|[0-7]{1,3}|x[0-9a-f]{1,2})`, LiteralStringEscape, nil},
-			{`\$(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*(\[\S+?\]|->(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)?`, LiteralStringInterpol, nil},
-			{`(\{\$\{)(.*?)(\}\})`, ByGroups(LiteralStringInterpol, UsingSelf("root"), LiteralStringInterpol), nil},
-			{`(\{)(\$.*?)(\})`, ByGroups(LiteralStringInterpol, UsingSelf("root"), LiteralStringInterpol), nil},
-			{`(\$\{)(\S+)(\})`, ByGroups(LiteralStringInterpol, NameVariable, LiteralStringInterpol), nil},
-			{`[${\\]`, LiteralStringDouble, nil},
-		},
 	},
-).SetAnalyser(func(text string) float32 {
+	"magicfuncs": {
-	if strings.Contains(text, "<?php") {
+		{Words(``, `\b`, `__construct`, `__destruct`, `__call`, `__callStatic`, `__get`, `__set`, `__isset`, `__unset`, `__sleep`, `__wakeup`, `__toString`, `__invoke`, `__set_state`, `__clone`, `__debugInfo`), NameFunctionMagic, nil},
-		return 0.5
+	},
-	}
+	"magicconstants": {
-	return 0.0
+		{Words(``, `\b`, `__LINE__`, `__FILE__`, `__DIR__`, `__FUNCTION__`, `__CLASS__`, `__TRAIT__`, `__METHOD__`, `__NAMESPACE__`), NameConstant, nil},
-})))
+	},
+	"classname": {
+		{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameClass, Pop(1)},
+	},
+	"functionname": {
+		Include("magicfuncs"),
+		{`(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*`, NameFunction, Pop(1)},
+		Default(Pop(1)),
+	},
+	"string": {
+		{`"`, LiteralStringDouble, Pop(1)},
+		{`[^{$"\\]+`, LiteralStringDouble, nil},
+		{`\\([nrt"$\\]|[0-7]{1,3}|x[0-9a-f]{1,2})`, LiteralStringEscape, nil},
+		{`\$(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*(\[\S+?\]|->(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w]|[^\x00-\x7f])*)?`, LiteralStringInterpol, nil},
+		{`(\{\$\{)(.*?)(\}\})`, ByGroups(LiteralStringInterpol, UsingSelf("root"), LiteralStringInterpol), nil},
+		{`(\{)(\$.*?)(\})`, ByGroups(LiteralStringInterpol, UsingSelf("root"), LiteralStringInterpol), nil},
+		{`(\$\{)(\S+)(\})`, ByGroups(LiteralStringInterpol, NameVariable, LiteralStringInterpol), nil},
+		{`[${\\]`, LiteralStringDouble, nil},
+	},
+}

lexers/circular/phtml.go

@@ -0,0 +1,34 @@
+package circular
+
+import (
+	"strings"
+
+	. "github.com/alecthomas/chroma" // nolint
+	"github.com/alecthomas/chroma/lexers/h"
+	"github.com/alecthomas/chroma/lexers/internal"
+)
+
+// PHTML lexer is PHP in HTML.
+var PHTML = internal.Register(DelegatingLexer(h.HTML, MustNewLexer(
+	&Config{
+		Name:            "PHTML",
+		Aliases:         []string{"phtml"},
+		Filenames:       []string{"*.phtml"},
+		MimeTypes:       []string{"application/x-php", "application/x-httpd-php", "application/x-httpd-php3", "application/x-httpd-php4", "application/x-httpd-php5"},
+		DotAll:          true,
+		CaseInsensitive: true,
+		EnsureNL:        true,
+	},
+	Rules{
+		"root": {
+			{`<\?(php)?`, CommentPreproc, Push("php")},
+			{`[^<]+`, Other, nil},
+			{`<`, Other, nil},
+		},
+	}.Merge(phpCommonRules),
+).SetAnalyser(func(text string) float32 {
+	if strings.Contains(text, "<?php") {
+		return 0.5
+	}
+	return 0.0
+})))

lexers/lexers_test.go

@@ -73,7 +73,7 @@ func TestLexers(t *testing.T) {
 			if os.Getenv("RECORD") == "true" {
 				// Update the expected file with the generated output of this lexer
 				f, err := os.Create(expectedFilename)
-				defer f.Close()
+				defer f.Close() // nolint: gosec
 				assert.NoError(t, err)
 				assert.NoError(t, formatters.JSON.Format(f, nil, chroma.Literator(actual...)))
 			} else {

lexers/testdata/php.actual

@@ -1,10 +1,3 @@
-<!DOCTYPE html>
-<html>
-<body>
-
-<h1>My first PHP page</h1>
-<?php
-
 $docs = $modx->getIterator('modResource', ["parent" => 84]);
 
 foreach($docs as $doc){
@@ -12,8 +5,5 @@ foreach($docs as $doc){
     $doc->set("content", preg_replace("/Some value/i", "Replacement", $q));
     print_r($doc->content);
     // $doc->save();
-} 
+}
 // some comment
-?>
-</body>
-</html>

lexers/testdata/php.expected

@@ -1,24 +1,4 @@
 [
-  {"type":"CommentPreproc","value":"\u003c!DOCTYPE html\u003e"},
-  {"type":"Text","value":"\n"},
-  {"type":"Punctuation","value":"\u003c"},
-  {"type":"NameTag","value":"html"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"\n"},
-  {"type":"Punctuation","value":"\u003c"},
-  {"type":"NameTag","value":"body"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"\n\n"},
-  {"type":"Punctuation","value":"\u003c"},
-  {"type":"NameTag","value":"h1"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"My first PHP page"},
-  {"type":"Punctuation","value":"\u003c/"},
-  {"type":"NameTag","value":"h1"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"\n"},
-  {"type":"CommentPreproc","value":"\u003c?php"},
-  {"type":"Text","value":"\n\n"},
   {"type":"NameVariable","value":"$docs"},
   {"type":"Text","value":" "},
   {"type":"Operator","value":"="},
@@ -81,16 +61,6 @@
   {"type":"Text","value":"\n    "},
   {"type":"CommentSingle","value":"// $doc-\u003esave();\n"},
   {"type":"Punctuation","value":"}"},
-  {"type":"Text","value":" \n"},
-  {"type":"CommentSingle","value":"// some comment\n"},
-  {"type":"CommentPreproc","value":"?\u003e"},
   {"type":"Text","value":"\n"},
-  {"type":"Punctuation","value":"\u003c/"},
+  {"type":"CommentSingle","value":"// some comment\n"}
-  {"type":"NameTag","value":"body"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"\n"},
-  {"type":"Punctuation","value":"\u003c/"},
-  {"type":"NameTag","value":"html"},
-  {"type":"Punctuation","value":"\u003e"},
-  {"type":"Text","value":"\n"}
 ]

lexers/testdata/phtml.actual

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html>
+<body>
+
+<h1>My first PHP page</h1>
+<?php
+
+$docs = $modx->getIterator('modResource', ["parent" => 84]);
+
+foreach($docs as $doc){
+    $q=$doc->content;
+    $doc->set("content", preg_replace("/Some value/i", "Replacement", $q));
+    print_r($doc->content);
+    // $doc->save();
+} 
+// some comment
+?>
+</body>
+</html>

lexers/testdata/phtml.expected

@@ -0,0 +1,96 @@
+[
+  {"type":"CommentPreproc","value":"\u003c!DOCTYPE html\u003e"},
+  {"type":"Text","value":"\n"},
+  {"type":"Punctuation","value":"\u003c"},
+  {"type":"NameTag","value":"html"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"\n"},
+  {"type":"Punctuation","value":"\u003c"},
+  {"type":"NameTag","value":"body"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"\n\n"},
+  {"type":"Punctuation","value":"\u003c"},
+  {"type":"NameTag","value":"h1"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"My first PHP page"},
+  {"type":"Punctuation","value":"\u003c/"},
+  {"type":"NameTag","value":"h1"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"\n"},
+  {"type":"CommentPreproc","value":"\u003c?php"},
+  {"type":"Text","value":"\n\n"},
+  {"type":"NameVariable","value":"$docs"},
+  {"type":"Text","value":" "},
+  {"type":"Operator","value":"="},
+  {"type":"Text","value":" "},
+  {"type":"NameVariable","value":"$modx"},
+  {"type":"Operator","value":"-\u003e"},
+  {"type":"NameAttribute","value":"getIterator"},
+  {"type":"Punctuation","value":"("},
+  {"type":"LiteralStringSingle","value":"'modResource'"},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"Punctuation","value":"["},
+  {"type":"LiteralStringDouble","value":"\"parent\""},
+  {"type":"Text","value":" "},
+  {"type":"Operator","value":"=\u003e"},
+  {"type":"Text","value":" "},
+  {"type":"LiteralNumberInteger","value":"84"},
+  {"type":"Punctuation","value":"]);"},
+  {"type":"Text","value":"\n\n"},
+  {"type":"Keyword","value":"foreach"},
+  {"type":"Punctuation","value":"("},
+  {"type":"NameVariable","value":"$docs"},
+  {"type":"Text","value":" "},
+  {"type":"Keyword","value":"as"},
+  {"type":"Text","value":" "},
+  {"type":"NameVariable","value":"$doc"},
+  {"type":"Punctuation","value":"){"},
+  {"type":"Text","value":"\n    "},
+  {"type":"NameVariable","value":"$q"},
+  {"type":"Operator","value":"="},
+  {"type":"NameVariable","value":"$doc"},
+  {"type":"Operator","value":"-\u003e"},
+  {"type":"NameAttribute","value":"content"},
+  {"type":"Punctuation","value":";"},
+  {"type":"Text","value":"\n    "},
+  {"type":"NameVariable","value":"$doc"},
+  {"type":"Operator","value":"-\u003e"},
+  {"type":"NameAttribute","value":"set"},
+  {"type":"Punctuation","value":"("},
+  {"type":"LiteralStringDouble","value":"\"content\""},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"NameOther","value":"preg_replace"},
+  {"type":"Punctuation","value":"("},
+  {"type":"LiteralStringDouble","value":"\"/Some value/i\""},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"LiteralStringDouble","value":"\"Replacement\""},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"NameVariable","value":"$q"},
+  {"type":"Punctuation","value":"));"},
+  {"type":"Text","value":"\n    "},
+  {"type":"NameOther","value":"print_r"},
+  {"type":"Punctuation","value":"("},
+  {"type":"NameVariable","value":"$doc"},
+  {"type":"Operator","value":"-\u003e"},
+  {"type":"NameAttribute","value":"content"},
+  {"type":"Punctuation","value":");"},
+  {"type":"Text","value":"\n    "},
+  {"type":"CommentSingle","value":"// $doc-\u003esave();\n"},
+  {"type":"Punctuation","value":"}"},
+  {"type":"Text","value":" \n"},
+  {"type":"CommentSingle","value":"// some comment\n"},
+  {"type":"CommentPreproc","value":"?\u003e"},
+  {"type":"Text","value":"\n"},
+  {"type":"Punctuation","value":"\u003c/"},
+  {"type":"NameTag","value":"body"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"\n"},
+  {"type":"Punctuation","value":"\u003c/"},
+  {"type":"NameTag","value":"html"},
+  {"type":"Punctuation","value":"\u003e"},
+  {"type":"Text","value":"\n"}
+]

regexp.go

@@ -160,6 +160,14 @@ func Tokenise(lexer Lexer, options *TokeniseOptions, text string) ([]Token, erro
 // Rules maps from state to a sequence of Rules.
 type Rules map[string][]Rule
 
+// Rename clones rules then a rule.
+func (r Rules) Rename(old, new string) Rules {
+	r = r.Clone()
+	r[new] = r[old]
+	delete(r, old)
+	return r
+}
+
 // Clone returns a clone of the Rules.
 func (r Rules) Clone() Rules {
 	out := map[string][]Rule{}