src/c2html.c

changeset 21
537aec525835
parent 20
ebbf0776c1bc
child 22
f463693b5eeb
     1.1 --- a/src/c2html.c	Fri Aug 30 11:23:44 2013 +0200
     1.2 +++ b/src/c2html.c	Thu Jan 23 09:19:37 2014 +0100
     1.3 @@ -1,7 +1,7 @@
     1.4  /*
     1.5   * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
     1.6   *
     1.7 - * Copyright 2013 Mike Becker. All rights reserved.
     1.8 + * Copyright 2014 Mike Becker. All rights reserved.
     1.9   *
    1.10   * Redistribution and use in source and binary forms, with or without
    1.11   * modification, are permitted provided that the following conditions are met:
    1.12 @@ -34,56 +34,10 @@
    1.13  #include <unistd.h>
    1.14  #include <ctype.h>
    1.15  
    1.16 +#include "javacodegen.h"
    1.17 +#include "ccodegen.h"
    1.18 +
    1.19  #define INPUTBUF_SIZE 2048
    1.20 -#define WORDBUF_SIZE 64
    1.21 -
    1.22 -const char* ckeywords[] = {
    1.23 -    "auto", "break", "case", "char", "const", "continue", "default", "do",
    1.24 -    "double", "else", "enum", "extern", "float", "for", "goto", "if", "int",
    1.25 -    "long", "register", "return", "short", "signed", "sizeof", "static",
    1.26 -    "struct", "switch", "typedef", "union", "unsigned", "void", "volatile",
    1.27 -    "while", NULL
    1.28 -};
    1.29 -
    1.30 -const char* jkeywords[] = {
    1.31 -    "abstract", "continue", "for", "new", "switch", "assert", "default", "goto",
    1.32 -    "package", "synchronized", "boolean", "do", "if", "private", "this",
    1.33 -    "break", "double", "implements", "protected", "throw", "byte", "else",
    1.34 -    "import", "public", "throws", "case", "enum", "instanceof", "return",
    1.35 -    "transient", "catch", "extends", "int", "short", "try", "char", "final",
    1.36 -    "interface", "static", "void", "class", "finally", "long", "strictfp",
    1.37 -    "volatile", "const", "float", "native", "super", "while", NULL
    1.38 -};
    1.39 -
    1.40 -#define iswordcharacter(c) (isalnum(c) || c=='_' || c=='#' || c=='@')
    1.41 -
    1.42 -int isctype(char *word, size_t len) {
    1.43 -    return (word[len-2] == '_' && word[len-1] == 't');
    1.44 -}
    1.45 -
    1.46 -int iscdirective(char *word) {
    1.47 -    return (word[0] == '#');
    1.48 -}
    1.49 -
    1.50 -int isjtype(char *word, size_t len) {
    1.51 -    return isupper(word[0]);
    1.52 -}
    1.53 -
    1.54 -int isjdirective(char *word) {
    1.55 -    return word[0] == '@';
    1.56 -}
    1.57 -
    1.58 -typedef struct _highlighter_t highlighter_t;
    1.59 -
    1.60 -struct _highlighter_t {
    1.61 -    const char** keywords;
    1.62 -    int(*istype)(char*,size_t);
    1.63 -    int(*isdirective)(char*);
    1.64 -    void(*parser)(char*,char*,highlighter_t*);
    1.65 -    int iscommentml;
    1.66 -    char word[WORDBUF_SIZE];
    1.67 -    char includefile[FILENAME_MAX];
    1.68 -};
    1.69  
    1.70  typedef struct {
    1.71      char* outfilename;
    1.72 @@ -169,190 +123,6 @@
    1.73      return inputfile;
    1.74  }
    1.75  
    1.76 -size_t writeescapedchar(char *dest, size_t dp, char c) {
    1.77 -    if (c == '>') {
    1.78 -        dest[dp++] = '&'; dest[dp++] = 'g'; dest[dp++] = 't'; dest[dp++] = ';';
    1.79 -    } else if (c == '<') {
    1.80 -        dest[dp++] = '&'; dest[dp++] = 'l'; dest[dp++] = 't'; dest[dp++] = ';';
    1.81 -    } else {
    1.82 -        dest[dp++] = c;
    1.83 -    }
    1.84 -
    1.85 -    return dp;
    1.86 -}
    1.87 -
    1.88 -int iskeyword(char *word, const char** keywords) {
    1.89 -    for (int i = 0 ; keywords[i] ; i++) {
    1.90 -        if (strncmp(keywords[i], word, WORDBUF_SIZE) == 0) {
    1.91 -            return 1;
    1.92 -        }
    1.93 -    }
    1.94 -    return 0;
    1.95 -}
    1.96 -
    1.97 -int iscapsonly(char *word, size_t wp) {
    1.98 -    for (size_t i = 0 ; i < wp ; i++) {
    1.99 -        if (!isupper(word[i]) && word[i] != '_') {
   1.100 -            return 0;
   1.101 -        }
   1.102 -    }
   1.103 -    return 1;
   1.104 -}
   1.105 -
   1.106 -void parseline(char *src, char *dest, highlighter_t *hltr) {
   1.107 -    hltr->parser(src, dest, hltr);
   1.108 -}
   1.109 -
   1.110 -void cjparseline(char *src, char *dest, highlighter_t *hltr) {
   1.111 -    size_t sp = 0, dp = 0;
   1.112 -    /* indent */
   1.113 -    while (isspace(src[sp])) {
   1.114 -        dest[dp++] = src[sp++];
   1.115 -    }
   1.116 -
   1.117 -    memset(hltr->word, 0, WORDBUF_SIZE);
   1.118 -    size_t wp = 0, ifp = 0;
   1.119 -    int isstring = 0, iscomment = 0, isinclude = 0, parseinclude = 0;
   1.120 -    int isescaping = 0;
   1.121 -
   1.122 -    if (hltr->iscommentml) {
   1.123 -        iscomment = 1;
   1.124 -        memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
   1.125 -        dp += 29;
   1.126 -    }
   1.127 -
   1.128 -    for (char c = src[sp] ; c ; c=src[++sp]) {
   1.129 -        /* comments */
   1.130 -        if (c == '/') {
   1.131 -            if (hltr->iscommentml && sp > 0 && src[sp-1] == '*') {
   1.132 -                iscomment = 0;
   1.133 -                hltr->iscommentml = 0;
   1.134 -                memcpy(&(dest[dp]), "/</span>", 8);
   1.135 -                dp += 8;
   1.136 -                continue;
   1.137 -            } else if (!iscomment && (src[sp+1] == '/' || src[sp+1] == '*')) {
   1.138 -                iscomment = 1;
   1.139 -                hltr->iscommentml = (src[sp+1] == '*');
   1.140 -                memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
   1.141 -                dp += 29;
   1.142 -            }
   1.143 -        }
   1.144 -
   1.145 -        if (iscomment) {
   1.146 -            if (c == '\n') {
   1.147 -                memcpy(&(dest[dp]), "</span>", 7);
   1.148 -                dp += 7;
   1.149 -            }
   1.150 -            dp = writeescapedchar(dest, dp, c);
   1.151 -        } else if (isinclude) {
   1.152 -            if (c == '<') {
   1.153 -                memcpy(&(dest[dp]), "<span class=\"c2html-stdinclude\">", 32);
   1.154 -                dp += 32;
   1.155 -                dp = writeescapedchar(dest, dp, c);
   1.156 -            } else if (c == '\"') {
   1.157 -                if (parseinclude) {
   1.158 -                    dest[dp++] = '\"';
   1.159 -                    dest[dp++] = '>';
   1.160 -                    memcpy(&(dest[dp]), hltr->includefile, ifp);
   1.161 -                    dp += ifp;
   1.162 -
   1.163 -                    dp = writeescapedchar(dest, dp, c);
   1.164 -                    memcpy(&(dest[dp]), "</a>", 4);
   1.165 -                    dp += 4;
   1.166 -                    parseinclude = 0;
   1.167 -                } else {
   1.168 -                    memcpy(&(dest[dp]),
   1.169 -                        "<a class=\"c2html-userinclude\" href=", 35);
   1.170 -                    dp += 35;
   1.171 -                    dp = writeescapedchar(dest, dp, c);
   1.172 -                    ifp = 0;
   1.173 -                    hltr->includefile[ifp++] = '\"';
   1.174 -                    parseinclude = 1;
   1.175 -                }
   1.176 -            } else if (c == '>') {
   1.177 -                dp = writeescapedchar(dest, dp, c);
   1.178 -                memcpy(&(dest[dp]), "</span>", 7);
   1.179 -                dp += 7;
   1.180 -            } else {
   1.181 -                if (parseinclude) {
   1.182 -                    hltr->includefile[ifp++] = c;
   1.183 -                }
   1.184 -                dp = writeescapedchar(dest, dp, c);
   1.185 -            }
   1.186 -        } else {
   1.187 -            /* strings */
   1.188 -            if (!isescaping && (c == '\'' || c == '\"')) {
   1.189 -                isstring ^= 1;
   1.190 -                if (isstring) {
   1.191 -                    memcpy(&(dest[dp]), "<span class=\"c2html-string\">", 28);
   1.192 -                    dp += 28;
   1.193 -                    dp = writeescapedchar(dest, dp, c);
   1.194 -                } else {
   1.195 -                    dp = writeescapedchar(dest, dp, c);
   1.196 -                    memcpy(&(dest[dp]), "</span>", 7);
   1.197 -                    dp += 7;
   1.198 -                }
   1.199 -            } else {
   1.200 -                if (isstring) {
   1.201 -                    dp = writeescapedchar(dest, dp, c);
   1.202 -                } else if (!iswordcharacter(c)) {
   1.203 -                    /* interpret word int_t */
   1.204 -                    if (wp > 0 && wp < WORDBUF_SIZE) {
   1.205 -                        int closespan = 1;
   1.206 -                        if (iskeyword(hltr->word, hltr->keywords)) {
   1.207 -                            memcpy(&(dest[dp]),
   1.208 -                                "<span class=\"c2html-keyword\">", 29);
   1.209 -                            dp += 29;
   1.210 -                        } else if (hltr->istype(hltr->word, wp)) {
   1.211 -                            memcpy(&(dest[dp]),
   1.212 -                                "<span class=\"c2html-type\">", 26);
   1.213 -                            dp += 26;
   1.214 -                        } else if (hltr->isdirective(hltr->word)) {
   1.215 -                            isinclude = !strncmp(
   1.216 -                                "#include", hltr->word, WORDBUF_SIZE);
   1.217 -                            memcpy(&(dest[dp]),
   1.218 -                                "<span class=\"c2html-directive\">", 31);
   1.219 -                            dp += 31;
   1.220 -                        } else if (iscapsonly(hltr->word, wp)) {
   1.221 -                            memcpy(&(dest[dp]),
   1.222 -                                "<span class=\"c2html-macroconst\">", 32);
   1.223 -                            dp += 32;
   1.224 -                        } else {
   1.225 -                            closespan = 0;
   1.226 -                        }
   1.227 -                        for (int i = 0 ; i < wp ; i++) {
   1.228 -                            dp = writeescapedchar(dest, dp, hltr->word[i]);
   1.229 -                        }
   1.230 -                        if (closespan) {
   1.231 -                            memcpy(&(dest[dp]), "</span>", 7);
   1.232 -                            dp += 7;
   1.233 -                        }
   1.234 -                    }
   1.235 -                    memset(hltr->word, 0, WORDBUF_SIZE);
   1.236 -                    wp = 0;
   1.237 -                    dp = writeescapedchar(dest, dp, c);
   1.238 -                } else {
   1.239 -                    /* read word */
   1.240 -                    if (wp < WORDBUF_SIZE) {
   1.241 -                        hltr->word[wp++] = c;
   1.242 -                    } else if (wp == WORDBUF_SIZE) {
   1.243 -                        for (int i = 0 ; i < WORDBUF_SIZE ; i++) {
   1.244 -                            dp = writeescapedchar(dest, dp, hltr->word[i]);
   1.245 -                        }
   1.246 -                        wp++;
   1.247 -                        dp = writeescapedchar(dest, dp, c);
   1.248 -                    } else {
   1.249 -                        dp = writeescapedchar(dest, dp, c);
   1.250 -                    }
   1.251 -                }
   1.252 -            }
   1.253 -
   1.254 -            isescaping = !isescaping & (c == '\\');
   1.255 -        }
   1.256 -    }
   1.257 -    dest[dp] = 0;
   1.258 -}
   1.259 -
   1.260  void printhelp() {
   1.261      printf("Formats source code using HTML.\n\nUsage:\n"
   1.262          "  c2html [Options] FILE\n\n"
   1.263 @@ -382,7 +152,7 @@
   1.264      highlighter.isdirective = iscdirective;
   1.265      highlighter.istype = isctype;
   1.266      highlighter.keywords = ckeywords;
   1.267 -    highlighter.parser = cjparseline;
   1.268 +    highlighter.parser = cparseline;
   1.269  
   1.270      char optc;
   1.271      while ((optc = getopt(argc, argv, "hjo:p")) != -1) {
   1.272 @@ -396,6 +166,7 @@
   1.273                  highlighter.isdirective = isjdirective;
   1.274                  highlighter.istype = isjtype;
   1.275                  highlighter.keywords = jkeywords;
   1.276 +                highlighter.parser = jparseline;
   1.277                  break;
   1.278              case 'p':
   1.279                  settings.highlight = 0;
   1.280 @@ -432,7 +203,7 @@
   1.281              int lnw = lnint(inputfile->count);
   1.282              for (int i = 0 ; i < inputfile->count ; i++) {
   1.283                  if (settings.highlight) {
   1.284 -                    parseline(inputfile->lines[i], line, &highlighter);
   1.285 +                    highlighter.parser(inputfile->lines[i], line, &highlighter);
   1.286                  } else {
   1.287                      line = inputfile->lines[i];
   1.288                  }

mercurial