File: unhtml.c

package info (click to toggle)
unhtml 2.3.9-6
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 252 kB
  • sloc: ansic: 486; makefile: 71; awk: 2
file content (293 lines) | stat: -rw-r--r-- 6,334 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
/*
 * File:        unhtml.c
 * Program:     unhtml
 * Written by:  Kevin Swan, 013639s@dragon.acadiau.ca
 * Completed:   February 3, 1998
 * Version:     2.3
 *
 * Usage:
 *     unhtml -version | [ filename ]
 *
 * Specification:
 * unhtml is a program which removes HTML formatting from a stream, writing
 * to output to a stream.  If it is invoked with a file name, it attempts
 * to read from the named file.  If it is invoked without a filename, it
 * reads from stdin.  It writes all output to stdout.
 */

#include <ctype.h>
#include <malloc.h>
#include <string.h>

#include "ops.h"
#include "esc.h"


char *VERSION = "unhtml  Version 2.3  Copyright (C) 1998 by Kevin Swan";
char *USAGE   = "unhtml -version | [ filename ]";



int main(int argc, char *argv[]) {

  /*
   * Variables local to the program.
   */
  FILE *inStream;
  char *tag;
  char *tmp;
  int tag_size;
  int ch;
  int i, j;



  /*
   * Do argument checking.  If more than one command line argument was
   * given, print a usage error.
   */
  if (argc > 2)
    fprintf (stderr, "Usage: %s\n", USAGE);

  /*
   * If the user simply requested the version of the program, print that
   * information and terminate.
   */
  if (argc == 2)
    if (strcmp (argv[1], "-version") == 0) {
      printf ("%s\n", VERSION);
      return 0;
    }

  /*
   * Allocate tag space, now that we know we need to do some actual work.
   */
  tag_size = MAX_TAG_SIZE;
  tag = (char *)malloc(tag_size);
  if (!tag) {
     fprintf (stderr, "Cannot malloc tag space (%d bytes).\n", tag_size);
     return 1;
  }

  /*
   * If an input file was specified, try to open a read stream on it.
   */
  if (argc == 2) {
    if ((inStream = fopen (argv[1], "r")) == NULL) {
      fprintf (stderr, "Error opening file [%s] for reading.\n", argv[1]);
      fprintf (stderr, "%s", USAGE);
      return 1;
    }
  } else
  /*
   * Otherwise, just use the standard input stream.
   */
    inStream = stdin;

  /*
   * Read tokens from the stream until we hit an opener for an HTML tag.
   */
  while (1) {

    ch = fgetc (inStream);

    /*
     * If we hit the end of the file, we're done.
     */
    if (ch == EOF)
      break;

    /*
     * If the character is not a tag opener, just print it.
     */
    if (ch != '<') {
      m_putchar (ch);
      continue;
    }

    /*
     * If we get this far, we've hit an HTML tag.  Read it into the
     * variable tag.
     */
    memset(tag, 0, tag_size);
    i = 0;
    while (ch != EOF) {
      tag[i] = ch;
      if (i == 1 && ch != '/' && !isalpha(ch)) {
	 m_putchar(tag[0]);
	 m_putchar(ch);
         break;
      }
      i++;
      if (ch == '>') {
	/*
	 * If it's really an html tag, then toss it.  Otherwise, it could
	 * have been just a '<' sign in the text.
	 */
	if (!isRealHtmlTag(tag)) {
	  fprintf(stderr, "not: %s\n",tag);
	  for (j = 0; j < i; j++)
            m_putchar(tag[j]);
	}

        break;
      }

			if (i >= tag_size-1) {
				tag_size <<= 1;
				tmp = realloc(tag, tag_size);
        if (!tmp) {
          fprintf (stderr, "Cannot malloc tag space (%d bytes).\n", tag_size);
          return 1;
        }
        tag = tmp;
      }

      ch = fgetc (inStream);
    }

    tag[i] = '\0';

#ifdef DEBUG
    fprintf (stderr, "Read in the tag \"%s\"\n", tag);
#endif

    /*
     * If it was a script opener, it is a special case.  We may find
     * '>' characters inside the <SCRIPT></SCRIPT> pair that are not
     * associated with a tag.  In addition, comment delimiters are
     * found inside the script tag pairs.  So, if we get a script
     * tag, skip ahead to the closing script tag.
     */
    if (isScriptOpeningTag (tag)) {

#ifdef DEBUG
      fprintf (stderr, "\"%s\" is a script opener.\n", tag);
#endif

      /*
       * This loop is necessary to ensure that we don't swallow up the
       * closing </SCRIPT> tag while filling the buffer if we happen to
       * hit a '<' character in some comparison in the scripting language.
       */
      while (1) {



#ifdef DEBUG
        fprintf (stderr, "1. Read till we hit a '<'.\n");
#endif

        /*
         * Read until we hit a '<'.
         */
        ch = fgetc (inStream);

        while (ch != EOF)
          if (ch == '<')
            break;
          else
            ch = fgetc (inStream);

        if (ch == EOF) {
          ungetc (ch, inStream);
          break;
        }



#ifdef DEBUG
        fprintf (stderr, "2. Read till we hit a '>' or a '<', filling the buffer.\n");
#endif

        /*
         * Hit a '<'.  Read till we hit a '>' or a '<', filling the buffer.
         */
        i = 1;
	memset(tag, 0, tag_size);
        tag[0] = '<';
        ch = fgetc (inStream);
        while (ch != EOF) {
          tag[i] = ch;
          i++;

					if (i >= tag_size-1) {
						tag_size <<= 1;
						tmp=realloc(tag, tag_size);
            if (!tmp) {
              fprintf (stderr, "Cannot malloc tag space (%d bytes).\n", tag_size);
              return 1;
            }
            tag = tmp;
          }

          if ((ch == '>') || (ch == '<'))
            break;

          ch = fgetc (inStream);

        } /* while */

        if (ch == EOF) {
          ungetc (ch, inStream);
          break;
        }

        tag[i] = '\0';

#ifdef DEBUG
        fprintf (stderr, "Read tag: \"%s\"\n", tag);
#endif

        if (ch == '<') {
          ungetc (ch, inStream);
          continue;
        } else
          if (isScriptClosingTag(tag))
            break;

      }

#ifdef DEBUG
      fprintf(stderr, "Got to the end of the script, found \"%s\"\n", tag);
#endif

      /*
       * At this point, we should be ready to read the first character
       * after the closing '>' of the </SCRIPT> tag.
       */
      continue;
    }

    /*
     * If it was a comment opener, skip to the comment closer.
     */
/*
    ch = fgetc (inStream);
    if (ch == EOF)
      break;
    for (i = 0 ; i < 10 ; i++) {
      if ((ch = fgetc (inStream)) == EOF)
        break;
      if (ch == '>')
        break;
      tag[i] = ch;
    }

    if (ch == EOF)
      break;
 */

  }

  m_putchar(EOF); /* for the rare case in which chars remain in bff */

  /*
   * Try to peacefully close the stream, if it is not stdin.
   */
  if (argc == 2)
    if (fclose(inStream))
      fprintf (stderr, "Error %d closing file.\n", errno);

  return 0;
}