src/c2html.c

Fri, 21 Jun 2013 13:32:31 +0200

author
Mike Becker <universe@uap-core.de>
date
Fri, 21 Jun 2013 13:32:31 +0200
changeset 10
925172e535a9
parent 9
6b1fba10c4cb
child 13
fe74bf2d5f27
permissions
-rw-r--r--

includes (with links in user includes)

     1 /*
     2  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
     3  *
     4  * Copyright 2013 Mike Becker. All rights reserved.
     5  *
     6  * Redistribution and use in source and binary forms, with or without
     7  * modification, are permitted provided that the following conditions are met:
     8  *
     9  *   1. Redistributions of source code must retain the above copyright
    10  *      notice, this list of conditions and the following disclaimer.
    11  *
    12  *   2. Redistributions in binary form must reproduce the above copyright
    13  *      notice, this list of conditions and the following disclaimer in the
    14  *      documentation and/or other materials provided with the distribution.
    15  *
    16  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
    17  * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
    18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
    19  * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
    20  * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
    21  * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
    22  * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
    23  * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
    24  * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
    25  * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
    26  * POSSIBILITY OF SUCH DAMAGE.
    27  *
    28  */
    30 #include <stdio.h>
    31 #include <stdlib.h>
    32 #include <string.h>
    33 #include <fcntl.h>
    34 #include <unistd.h>
    35 #include <ctype.h>
    37 #define INPUTBUF_SIZE 2048
    38 #define WORDBUF_SIZE 16
    40 #define istype(word, len) (word[len-2] == '_' && word[len-1] == 't')
    41 #define isdirective(word) (word[0] == '#')
    43 const char* keywords[] = {
    44   "auto", "break", "case", "char", "const", "continue", "default", "do", 
    45   "double", "else", "enum", "extern", "float", "for", "goto", "if", "int", 
    46   "long", "register", "return", "short", "signed", "sizeof", "static", "struct", 
    47   "switch", "typedef", "union", "unsigned", "void", "volatile", "while", NULL
    48 };
    51 typedef struct {
    52   size_t count;
    53   size_t capacity;
    54   size_t maxlinewidth;
    55   char** lines;
    56 } inputfile_t;
    58 inputfile_t *inputfilebuffer(size_t capacity) {
    59   inputfile_t *inputfile = (inputfile_t*) malloc(sizeof(inputfile_t));
    60   inputfile->lines = (char**) malloc(capacity * sizeof(char*));
    61   inputfile->capacity = capacity;
    62   inputfile->count = 0;
    63   inputfile->maxlinewidth = 0;
    65   return inputfile;
    66 }
    68 void addline(inputfile_t *inputfile, char* line, size_t width) {
    69   char *l = (char*) malloc(width+1);
    70   memcpy(l, line, width);
    71   l[width] = 0;
    72   if (inputfile->count >= inputfile->capacity) {
    73     inputfile->capacity <<= 1;
    74     inputfile->lines = realloc(inputfile->lines, inputfile->capacity);
    75   }
    76   inputfile->lines[inputfile->count] = l;
    77   inputfile->maxlinewidth =
    78           width > inputfile->maxlinewidth ? width : inputfile->maxlinewidth;
    79   inputfile->count++;
    80 }
    82 void freeinputfilebuffer(inputfile_t *inputfile) {
    83   for (int i = 0 ; i < inputfile->count ; i++) {
    84     free(inputfile->lines[i]);
    85   }
    86   free(inputfile->lines);
    87   free(inputfile);
    88 }
    90 inputfile_t *readinput(char *filename) {
    92   int fd = open(filename, O_RDONLY);
    93   if (fd == -1) return NULL;
    95   inputfile_t *inputfile = inputfilebuffer(512);
    97   char buf[INPUTBUF_SIZE];
    98   ssize_t r;
   100   size_t maxlinewidth = 256;
   101   char *line = (char*) malloc(maxlinewidth);
   102   size_t col = 0;
   104   while ((r = read(fd, buf, INPUTBUF_SIZE)) > 0) {
   105     for (size_t i = 0 ; i < r ; i++) {
   106       if (col >= maxlinewidth-4) {
   107         maxlinewidth <<= 1;
   108         line = realloc(line, maxlinewidth);
   109       }
   111       if (buf[i] == '\n') {
   112         line[col++] = '\n';
   113         line[col] = 0;
   114         addline(inputfile, line, col);        
   115         col = 0;
   116       } else {
   117         line[col++] = buf[i];
   118       }
   119     }
   120   }
   122   free(line);
   124   close(fd);
   126   return inputfile;
   127 }
   129 size_t writeescapedchar(char *dest, size_t dp, char c) {
   130   if (c == '>') {
   131     dest[dp++] = '&'; dest[dp++] = 'g';
   132     dest[dp++] = 't'; dest[dp++] = ';';
   133   } else if (c == '<') {
   134     dest[dp++] = '&'; dest[dp++] = 'l';
   135     dest[dp++] = 't'; dest[dp++] = ';';
   136   } else {
   137     dest[dp++] = c;
   138   }
   140   return dp;
   141 }
   143 int iskeyword(char *word) {
   144   for (int i = 0 ; keywords[i] ; i++) {
   145     if (strncmp(keywords[i], word, WORDBUF_SIZE) == 0) {
   146       return 1;
   147     }
   148   }
   149   return 0;
   150 }
   152 int iscapsonly(char *word, size_t wp) {
   153   for (size_t i = 0 ; i < wp ; i++) {
   154     if (!isupper(word[i]) && word[i] != '_') {
   155       return 0;
   156     }
   157   }
   158   return 1;
   159 }
   161 void parseline(char *src, char *dest) {
   162   size_t sp = 0, dp = 0;
   163   /* indent */
   164   while (isspace(src[sp])) {
   165     dest[dp++] = src[sp++];
   166   }
   168   static char word[WORDBUF_SIZE];
   169   static char includefile[FILENAME_MAX];
   171   memset(word, 0, WORDBUF_SIZE);
   172   size_t wp = 0, ifp = 0;
   173   int isstring = 0, iscomment = 0, isinclude = 0, parseinclude = 0;
   174   static int iscommentml;
   175   int isescaping = 0;
   177   if (iscommentml) {
   178     iscomment = 1;
   179     memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
   180     dp += 29;
   181   }
   183   for (char c = src[sp] ; c ; c=src[++sp]) {
   184     /* comments */
   185     if (c == '/') {
   186       if (iscommentml && sp > 0 && src[sp-1] == '*') {
   187         iscomment = 0;
   188         iscommentml = 0;
   189         memcpy(&(dest[dp]), "/</span>", 8);
   190         dp += 8;
   191         continue;
   192       } else if (!iscomment && (src[sp+1] == '/' || src[sp+1] == '*')) {
   193         iscomment = 1;
   194         iscommentml = (src[sp+1] == '*');
   195         memcpy(&(dest[dp]), "<span class=\"c2html-comment\">", 29);
   196         dp += 29;
   197       }
   198     }
   200     if (iscomment) {
   201       if (c == '\n') {
   202         memcpy(&(dest[dp]), "</span>", 7);
   203         dp += 7;
   204       }
   205       dp = writeescapedchar(dest, dp, c);
   206     } else if (isinclude) {
   207       if (c == '<') {
   208         memcpy(&(dest[dp]), "<span class=\"c2html-stdinclude\">", 32);
   209         dp += 32;
   210         dp = writeescapedchar(dest, dp, c);
   211       } else if (c == '\"') {
   212         if (parseinclude) {
   213           dest[dp++] = '\"';
   214           dest[dp++] = '>';
   215           memcpy(&(dest[dp]), includefile, ifp);
   216           dp += ifp;
   218           dp = writeescapedchar(dest, dp, c);
   219           memcpy(&(dest[dp]), "</a>", 4);
   220           dp += 4;
   221           parseinclude = 0;
   222         } else {
   223           memcpy(&(dest[dp]), "<a class=\"c2html-userinclude\" href=", 35);
   224           dp += 35;
   225           dp = writeescapedchar(dest, dp, c);
   226           ifp = 0;
   227           includefile[ifp++] = '\"';
   228           parseinclude = 1;
   229         }
   230       } else if (c == '>') {
   231         dp = writeescapedchar(dest, dp, c);
   232         memcpy(&(dest[dp]), "</span>", 7);
   233         dp += 7;
   234       } else {
   235         if (parseinclude) {
   236           includefile[ifp++] = c;
   237         }
   238         dp = writeescapedchar(dest, dp, c);
   239       }
   240     } else {
   241       /* strings */
   242       if (!isescaping && (c == '\'' || c == '\"')) {
   243         isstring ^= 1;
   244         if (isstring) {
   245           memcpy(&(dest[dp]), "<span class=\"c2html-string\">", 28);
   246           dp += 28;
   247           dp = writeescapedchar(dest, dp, c);
   248         } else {
   249           dp = writeescapedchar(dest, dp, c);
   250           memcpy(&(dest[dp]), "</span>", 7);
   251           dp += 7;
   252         }
   253       } else {
   254         if (isstring) {
   255           dp = writeescapedchar(dest, dp, c);
   256         } else if (!isalnum(c) && c != '_' && c != '#' && c != '.') {
   257           /* interpret word int_t */
   258           if (wp > 0 && wp < WORDBUF_SIZE) {
   259             int closespan = 1;
   260             if (iskeyword(word)) {
   261               memcpy(&(dest[dp]), "<span class=\"c2html-keyword\">", 29);
   262               dp += 29;
   263             } else if (istype(word, wp)) {
   264               memcpy(&(dest[dp]), "<span class=\"c2html-type\">", 26);
   265               dp += 26;
   266             } else if (isdirective(word)) {
   267               isinclude = !strncmp("#include", word, WORDBUF_SIZE);
   268               memcpy(&(dest[dp]), "<span class=\"c2html-directive\">", 31);
   269               dp += 31;
   270             } else if (iscapsonly(word, wp)) {
   271               memcpy(&(dest[dp]), "<span class=\"c2html-macroconst\">", 32);
   272               dp += 32;
   273             } else {
   274               closespan = 0;
   275             }
   276             for (int i = 0 ; i < wp ; i++) {
   277               dp = writeescapedchar(dest, dp, word[i]);
   278             }
   279             if (closespan) {
   280               memcpy(&(dest[dp]), "</span>", 7);
   281               dp += 7;
   282             }
   283           }
   284           memset(word, 0, WORDBUF_SIZE);
   285           wp = 0;
   286           dp = writeescapedchar(dest, dp, c);
   287         } else {
   288           /* read word */
   289           if (wp < WORDBUF_SIZE) {
   290             word[wp++] = c;
   291           } else if (wp == WORDBUF_SIZE) {
   292             for (int i = 0 ; i < WORDBUF_SIZE ; i++) {
   293               dp = writeescapedchar(dest, dp, word[i]);
   294             }
   295             wp++;
   296             dp = writeescapedchar(dest, dp, c);
   297           } else {
   298             dp = writeescapedchar(dest, dp, c);
   299           }
   300         }
   301       }
   303       isescaping = !isescaping & (c == '\\');
   304     }
   305   }
   306   dest[dp] = 0;
   307 }
   309 void printhelp() {
   310   printf("Formats source code using HTML.\n\nUsage:\n"
   311       "  c2html [FILE...]"
   312       "\n");
   315 }
   317 int lnint(size_t lnc) {
   318   int w = 1, p = 1;
   319   while ((p*=10) < lnc) w++;
   320   return w;
   321 }
   323 int main(int argc, char** argv) {
   325   if (argc == 1) {
   326     printhelp();
   327     return 0;
   328   } else {
   330     inputfile_t *inputfile = readinput(argv[1]);
   331     if (inputfile) {
   332       printf("<pre>\n");
   333       char *line = (char*) malloc(inputfile->maxlinewidth*64);
   334       int lnw = lnint(inputfile->count);
   335       for (int i = 0 ; i < inputfile->count ; i++) {
   336         parseline(inputfile->lines[i], line);
   337         printf("<span class=\"c2html-lineno\">%*d:</span> %s",
   338             lnw, i+1, line);
   339       }
   340       free(line);
   341       printf("</pre>\n");
   342       freeinputfilebuffer(inputfile);
   343     }
   345     return 0;
   346   }
   347 }

mercurial