| 1 | // Scintilla source code edit control |
| 2 | /** @file LexConf.cxx |
| 3 | ** Lexer for Apache Configuration Files. |
| 4 | ** |
| 5 | ** First working version contributed by Ahmad Zawawi <ahmad.zawawi@gmail.com> on October 28, 2000. |
| 6 | ** i created this lexer because i needed something pretty when dealing |
| 7 | ** when Apache Configuration files... |
| 8 | **/ |
| 9 | // Copyright 1998-2001 by Neil Hodgson <neilh@scintilla.org> |
| 10 | // The License.txt file describes the conditions under which this software may be distributed. |
| 11 | |
| 12 | #include <stdlib.h> |
| 13 | #include <string.h> |
| 14 | #include <stdio.h> |
| 15 | #include <stdarg.h> |
| 16 | #include <assert.h> |
| 17 | #include <ctype.h> |
| 18 | |
| 19 | #include <string> |
| 20 | #include <string_view> |
| 21 | |
| 22 | #include "ILexer.h" |
| 23 | #include "Scintilla.h" |
| 24 | #include "SciLexer.h" |
| 25 | |
| 26 | #include "WordList.h" |
| 27 | #include "LexAccessor.h" |
| 28 | #include "Accessor.h" |
| 29 | #include "StyleContext.h" |
| 30 | #include "CharacterSet.h" |
| 31 | #include "LexerModule.h" |
| 32 | |
| 33 | using namespace Lexilla; |
| 34 | |
| 35 | static void ColouriseConfDoc(Sci_PositionU startPos, Sci_Position length, int, WordList *keywordLists[], Accessor &styler) |
| 36 | { |
| 37 | int state = SCE_CONF_DEFAULT; |
| 38 | char chNext = styler[startPos]; |
| 39 | Sci_Position lengthDoc = startPos + length; |
| 40 | // create a buffer large enough to take the largest chunk... |
| 41 | char *buffer = new char[length+1]; |
| 42 | Sci_Position bufferCount = 0; |
| 43 | |
| 44 | // this assumes that we have 2 keyword list in conf.properties |
| 45 | WordList &directives = *keywordLists[0]; |
| 46 | WordList ¶ms = *keywordLists[1]; |
| 47 | |
| 48 | // go through all provided text segment |
| 49 | // using the hand-written state machine shown below |
| 50 | styler.StartAt(startPos); |
| 51 | styler.StartSegment(startPos); |
| 52 | for (Sci_Position i = startPos; i < lengthDoc; i++) { |
| 53 | char ch = chNext; |
| 54 | chNext = styler.SafeGetCharAt(i + 1); |
| 55 | |
| 56 | if (styler.IsLeadByte(ch)) { |
| 57 | chNext = styler.SafeGetCharAt(i + 2); |
| 58 | i++; |
| 59 | continue; |
| 60 | } |
| 61 | switch(state) { |
| 62 | case SCE_CONF_DEFAULT: |
| 63 | if( ch == '\n' || ch == '\r' || ch == '\t' || ch == ' ') { |
| 64 | // whitespace is simply ignored here... |
| 65 | styler.ColourTo(i,SCE_CONF_DEFAULT); |
| 66 | break; |
| 67 | } else if( ch == '#' ) { |
| 68 | // signals the start of a comment... |
| 69 | state = SCE_CONF_COMMENT; |
| 70 | styler.ColourTo(i,SCE_CONF_COMMENT); |
| 71 | } else if( ch == '.' /*|| ch == '/'*/) { |
| 72 | // signals the start of a file... |
| 73 | state = SCE_CONF_EXTENSION; |
| 74 | styler.ColourTo(i,SCE_CONF_EXTENSION); |
| 75 | } else if( ch == '"') { |
| 76 | state = SCE_CONF_STRING; |
| 77 | styler.ColourTo(i,SCE_CONF_STRING); |
| 78 | } else if( IsASCII(ch) && ispunct(ch) ) { |
| 79 | // signals an operator... |
| 80 | // no state jump necessary for this |
| 81 | // simple case... |
| 82 | styler.ColourTo(i,SCE_CONF_OPERATOR); |
| 83 | } else if( IsASCII(ch) && isalpha(ch) ) { |
| 84 | // signals the start of an identifier |
| 85 | bufferCount = 0; |
| 86 | buffer[bufferCount++] = static_cast<char>(tolower(ch)); |
| 87 | state = SCE_CONF_IDENTIFIER; |
| 88 | } else if( IsASCII(ch) && isdigit(ch) ) { |
| 89 | // signals the start of a number |
| 90 | bufferCount = 0; |
| 91 | buffer[bufferCount++] = ch; |
| 92 | //styler.ColourTo(i,SCE_CONF_NUMBER); |
| 93 | state = SCE_CONF_NUMBER; |
| 94 | } else { |
| 95 | // style it the default style.. |
| 96 | styler.ColourTo(i,SCE_CONF_DEFAULT); |
| 97 | } |
| 98 | break; |
| 99 | |
| 100 | case SCE_CONF_COMMENT: |
| 101 | // if we find a newline here, |
| 102 | // we simply go to default state |
| 103 | // else continue to work on it... |
| 104 | if( ch == '\n' || ch == '\r' ) { |
| 105 | state = SCE_CONF_DEFAULT; |
| 106 | } else { |
| 107 | styler.ColourTo(i,SCE_CONF_COMMENT); |
| 108 | } |
| 109 | break; |
| 110 | |
| 111 | case SCE_CONF_EXTENSION: |
| 112 | // if we find a non-alphanumeric char, |
| 113 | // we simply go to default state |
| 114 | // else we're still dealing with an extension... |
| 115 | if( (IsASCII(ch) && isalnum(ch)) || (ch == '_') || |
| 116 | (ch == '-') || (ch == '$') || |
| 117 | (ch == '/') || (ch == '.') || (ch == '*') ) |
| 118 | { |
| 119 | styler.ColourTo(i,SCE_CONF_EXTENSION); |
| 120 | } else { |
| 121 | state = SCE_CONF_DEFAULT; |
| 122 | chNext = styler[i--]; |
| 123 | } |
| 124 | break; |
| 125 | |
| 126 | case SCE_CONF_STRING: |
| 127 | // if we find the end of a string char, we simply go to default state |
| 128 | // else we're still dealing with an string... |
| 129 | if( (ch == '"' && styler.SafeGetCharAt(i-1)!='\\') || (ch == '\n') || (ch == '\r') ) { |
| 130 | state = SCE_CONF_DEFAULT; |
| 131 | } |
| 132 | styler.ColourTo(i,SCE_CONF_STRING); |
| 133 | break; |
| 134 | |
| 135 | case SCE_CONF_IDENTIFIER: |
| 136 | // stay in CONF_IDENTIFIER state until we find a non-alphanumeric |
| 137 | if( (IsASCII(ch) && isalnum(ch)) || (ch == '_') || (ch == '-') || (ch == '/') || (ch == '$') || (ch == '.') || (ch == '*')) { |
| 138 | buffer[bufferCount++] = static_cast<char>(tolower(ch)); |
| 139 | } else { |
| 140 | state = SCE_CONF_DEFAULT; |
| 141 | buffer[bufferCount] = '\0'; |
| 142 | |
| 143 | // check if the buffer contains a keyword, and highlight it if it is a keyword... |
| 144 | if(directives.InList(buffer)) { |
| 145 | styler.ColourTo(i-1,SCE_CONF_DIRECTIVE ); |
| 146 | } else if(params.InList(buffer)) { |
| 147 | styler.ColourTo(i-1,SCE_CONF_PARAMETER ); |
| 148 | } else if(strchr(buffer,'/') || strchr(buffer,'.')) { |
| 149 | styler.ColourTo(i-1,SCE_CONF_EXTENSION); |
| 150 | } else { |
| 151 | styler.ColourTo(i-1,SCE_CONF_DEFAULT); |
| 152 | } |
| 153 | |
| 154 | // push back the faulty character |
| 155 | chNext = styler[i--]; |
| 156 | |
| 157 | } |
| 158 | break; |
| 159 | |
| 160 | case SCE_CONF_NUMBER: |
| 161 | // stay in CONF_NUMBER state until we find a non-numeric |
| 162 | if( (IsASCII(ch) && isdigit(ch)) || ch == '.') { |
| 163 | buffer[bufferCount++] = ch; |
| 164 | } else { |
| 165 | state = SCE_CONF_DEFAULT; |
| 166 | buffer[bufferCount] = '\0'; |
| 167 | |
| 168 | // Colourize here... |
| 169 | if( strchr(buffer,'.') ) { |
| 170 | // it is an IP address... |
| 171 | styler.ColourTo(i-1,SCE_CONF_IP); |
| 172 | } else { |
| 173 | // normal number |
| 174 | styler.ColourTo(i-1,SCE_CONF_NUMBER); |
| 175 | } |
| 176 | |
| 177 | // push back a character |
| 178 | chNext = styler[i--]; |
| 179 | } |
| 180 | break; |
| 181 | |
| 182 | } |
| 183 | } |
| 184 | delete []buffer; |
| 185 | } |
| 186 | |
| 187 | static const char * const confWordListDesc[] = { |
| 188 | "Directives" , |
| 189 | "Parameters" , |
| 190 | 0 |
| 191 | }; |
| 192 | |
| 193 | LexerModule lmConf(SCLEX_CONF, ColouriseConfDoc, "conf" , 0, confWordListDesc); |
| 194 | |