/src/ghostpdl/base/sa85d.c

Source
/* Copyright (C) 2001-2026 Artifex Software, Inc.
   All Rights Reserved.

   This software is provided AS-IS with no warranty, either express or
   implied.

   This software is distributed under license and may not be copied,
   modified or distributed except as expressly authorized under the terms
   of the license contained in the file LICENSE in this distribution.

   Refer to licensing information at http://www.artifex.com or contact
   Artifex Software, Inc.,  39 Mesa Street, Suite 108A, San Francisco,
   CA 94129, USA, for further information.
*/


/* ASCII85Decode filter */
#include "std.h"
#include "strimpl.h"
#include "sa85d.h"
#include "scanchar.h"

/* ------ ASCII85Decode ------ */

private_st_A85D_state();

/* Initialize the state */
static int
s_A85D_init(stream_state * st)
{
    stream_A85D_state *const ss = (stream_A85D_state *) st;

    s_A85D_init_inline(ss);
    return 0;
}

/* Process a buffer */
static int a85d_finish(int, ulong, stream_cursor_write *);
static int
s_A85D_process(stream_state * st, stream_cursor_read * pr,
               stream_cursor_write * pw, bool last)
{
    stream_A85D_state *const ss = (stream_A85D_state *) st;
    register const byte *p = pr->ptr;
    register byte *q = pw->ptr;
    /* stop processing early unless the target is empty (last == true)  */
    /* to make sure we consume the EOD marker correctly. The EOD marker */
    /* might be as many as 6 characters after the last valid data char  */
    /* D <cr> <lf> '~' <cr> <lf> '>' where 'D' is a data character.     */
    const byte *rlimit = pr->limit - (last ? 0 : 7); /* max EOD len + 1 */
    const byte *r = max(p, rlimit);
    byte *wlimit = pw->limit;
    int ccount = ss->odd;
    ulong word = ss->word;
    int status = 0;

    /* scan to make sure that an EOD isn't fully contained in the */
    /* last part of the buffer (between rlimit and pr->limit).    */
    while (r < pr->limit) {
        if (*++r == '~')
            while (r < pr->limit)
                if (*++r == '>') {
                    /* we have both characters of a complete EOD. */
                    rlimit = pr->limit; /* go ahead and process everything */
                    r = rlimit;   /* break out of the while loops */
                    break;
                }
    }
    while (p < rlimit) {
        int ch = *++p;
        uint ccode = ch - '!';

        if (ccode < 85) { /* catches ch < '!' as well */
            if (ccount == 4) {
                /*
                 * We've completed a 32-bit group.  Make sure we have
                 * room for it in the output.
                 */
                if (wlimit - q < 4) {
                    p--;
                    status = 1;
                    break;
                }
                /* Check for overflow condition, throw ioerror if so */
                if (word >= 0x03030303 && ccode > 0) {
                    status = ERRC;
                    break;
                }
                word = word * 85 + ccode;
                q[1] = (byte) (word >> 24);
                q[2] = (byte) (word >> 16);
                q[3] = (byte) ((uint) word >> 8);
                q[4] = (byte) word;
                q += 4;
                word = 0;
                ccount = 0;
            } else {
                word = word * 85 + ccode;
                ++ccount;
            }
        } else if (ch == 'z' && ccount == 0) {
            if (wlimit - q < 4) {
                p--;
                status = 1;
                break;
            }
            q[1] = q[2] = q[3] = q[4] = 0,
                q += 4;
        } else if (scan_char_decoder[ch] == ctype_space)
            DO_NOTHING;
        else if (ch == '~') {
            int i = 1;

            if ((int)(wlimit - q) < ccount - 1) {
                status = 1;
                p--;
                break;
            }

            rlimit = pr->limit;   /* Here we use the real "limit" */
            /* Handle odd bytes. */
            if (p == rlimit) {
                if (!last)
                  p--;
                else if (ss->pdf_rules)
                  goto finish;
                else
                    status = ERRC;
                break;
            }

            /* According to PLRM 3rd, if the A85 filter encounters '~',
             * the next character must be '>'.
             * And any other characters should raise an ioerror.
             * But Adobe Acrobat allows CR/LF between ~ and >.
             * So we allow CR/LF between them. */
            /* PDF further relaxes the requirements and accepts bare '~'.
             */
            while ((p + i <= rlimit) && (p[i] == 13 || p[i] == 10))
                i++;
            if (p + i <= rlimit && p[i] != '>') {
                if (ss->pdf_rules) {
                    if (p[i] == 13 || p[i] == 10) {
                        if (!last)
                            break;
                    } else {
                        p--;
                    }
                } else {
                    if (p + i == rlimit) {
                        if (last)
                            status = ERRC;
                        else
                            p--; /* we'll see the '~' after filling the buffer */
                    }
                    break;
                }
            }
          finish:
            if (p + i <= rlimit)
                p += i;    /* advance to the '>' */
            else
                p = rlimit; /* Can happen if the '>' is missing */
            pw->ptr = q;
            status = a85d_finish(ccount, word, pw);
            q = pw->ptr;
            break;
        } else {   /* syntax error or exception */
            status = ERRC;
            break;
        }
    }
    pw->ptr = q;
    if (status == 0 && last) {
        if ((int)(wlimit - q) < ccount - 1)
            status = 1;
        else if (ss->require_eod)
            status = ERRC;
        else
            status = a85d_finish(ccount, word, pw);
    }
    pr->ptr = p;
    ss->odd = ccount;
    ss->word = word;
    return status;
}
/* Handle the end of input data. */
static int
a85d_finish(int ccount, ulong word, stream_cursor_write * pw)
{
    /* Assume there is enough room in the output buffer! */
    byte *q = pw->ptr;
    int status = EOFC;

    switch (ccount) {
        case 0:
            break;
        case 1:   /* syntax error */
            status = ERRC;
            break;
        case 2:   /* 1 odd byte */
            word = word * (85L * 85 * 85) + 85L * 85 * 85 - 1L;
            goto o1;
        case 3:   /* 2 odd bytes */
            word = word * (85L * 85) + 85L * 85L - 1L;
            goto o2;
        case 4:   /* 3 odd bytes */
            word = word * 85L + 84L;
            q[3] = (byte) (word >> 8);
o2:     q[2] = (byte) (word >> 16);
o1:     q[1] = (byte) (word >> 24);
            q += ccount - 1;
            pw->ptr = q;
    }
    return status;
}

/* Stream template */
const stream_template s_A85D_template = {
    &st_A85D_state, s_A85D_init, s_A85D_process, 2, 4
};

Coverage Report

Created: 2026-10-28 08:05

Line	Count	Source
1		/* Copyright (C) 2001-2026 Artifex Software, Inc.
2		All Rights Reserved.
3
4		This software is provided AS-IS with no warranty, either express or
5		implied.
6
7		This software is distributed under license and may not be copied,
8		modified or distributed except as expressly authorized under the terms
9		of the license contained in the file LICENSE in this distribution.
10
11		Refer to licensing information at http://www.artifex.com or contact
12		Artifex Software, Inc., 39 Mesa Street, Suite 108A, San Francisco,
13		CA 94129, USA, for further information.
14		*/
15
16
17		/* ASCII85Decode filter */
18		#include "std.h"
19		#include "strimpl.h"
20		#include "sa85d.h"
21		#include "scanchar.h"
22
23		/* ------ ASCII85Decode ------ */
24
25		private_st_A85D_state();
26
27		/* Initialize the state */
28		static int
29		s_A85D_init(stream_state * st)
30	639	{
31	639	stream_A85D_state const ss = (stream_A85D_state ) st;
32
33	639	s_A85D_init_inline(ss);
34	639	return 0;
35	639	}
36
37		/* Process a buffer */
38		static int a85d_finish(int, ulong, stream_cursor_write *);
39		static int
40		s_A85D_process(stream_state * st, stream_cursor_read * pr,
41		stream_cursor_write * pw, bool last)
42	531k	{
43	531k	stream_A85D_state const ss = (stream_A85D_state ) st;
44	531k	register const byte *p = pr->ptr;
45	531k	register byte *q = pw->ptr;
46		/* stop processing early unless the target is empty (last == true) */
47		/* to make sure we consume the EOD marker correctly. The EOD marker */
48		/* might be as many as 6 characters after the last valid data char */
49		/* D <cr> <lf> '~' <cr> <lf> '>' where 'D' is a data character. */
50	531k	const byte rlimit = pr->limit - (last ? 0 : 7); / max EOD len + 1 */
51	531k	const byte *r = max(p, rlimit);
52	531k	byte *wlimit = pw->limit;
53	531k	int ccount = ss->odd;
54	531k	ulong word = ss->word;
55	531k	int status = 0;
56
57		/* scan to make sure that an EOD isn't fully contained in the */
58		/* last part of the buffer (between rlimit and pr->limit). */
59	1.20M	while (r < pr->limit) {
60	674k	if (*++r == '~')
61	3.55M	while (r < pr->limit)
62	3.03M	if (*++r == '>') {
63		/* we have both characters of a complete EOD. */
64	461	rlimit = pr->limit; /* go ahead and process everything */
65	461	r = rlimit; /* break out of the while loops */
66	461	break;
67	461	}
68	674k	}
69	6.23M	while (p < rlimit) {
70	6.23M	int ch = *++p;
71	6.23M	uint ccode = ch - '!';
72
73	6.23M	if (ccode < 85) { /* catches ch < '!' as well */
74	5.68M	if (ccount == 4) {
75		/*
76		* We've completed a 32-bit group. Make sure we have
77		* room for it in the output.
78		*/
79	1.13M	if (wlimit - q < 4) {
80	1.38k	p--;
81	1.38k	status = 1;
82	1.38k	break;
83	1.38k	}
84		/* Check for overflow condition, throw ioerror if so */
85	1.13M	if (word >= 0x03030303 && ccode > 0) {
86	180	status = ERRC;
87	180	break;
88	180	}
89	1.13M	word = word * 85 + ccode;
90	1.13M	q[1] = (byte) (word >> 24);
91	1.13M	q[2] = (byte) (word >> 16);
92	1.13M	q[3] = (byte) ((uint) word >> 8);
93	1.13M	q[4] = (byte) word;
94	1.13M	q += 4;
95	1.13M	word = 0;
96	1.13M	ccount = 0;
97	4.54M	} else {
98	4.54M	word = word * 85 + ccode;
99	4.54M	++ccount;
100	4.54M	}
101	5.68M	} else if (ch == 'z' && ccount == 0) {
102	558	if (wlimit - q < 4) {
103	0	p--;
104	0	status = 1;
105	0	break;
106	0	}
107	558	q[1] = q[2] = q[3] = q[4] = 0,
108	558	q += 4;
109	544k	} else if (scan_char_decoder[ch] == ctype_space)
110	544k	DO_NOTHING;
111	525k	else if (ch == '~') {
112	525k	int i = 1;
113
114	525k	if ((int)(wlimit - q) < ccount - 1) {
115	108	status = 1;
116	108	p--;
117	108	break;
118	108	}
119
120	524k	rlimit = pr->limit; /* Here we use the real "limit" */
121		/* Handle odd bytes. */
122	524k	if (p == rlimit) {
123	18	if (!last)
124	0	p--;
125	18	else if (ss->pdf_rules)
126	0	goto finish;
127	18	else
128	18	status = ERRC;
129	18	break;
130	18	}
131
132		/* According to PLRM 3rd, if the A85 filter encounters '~',
133		* the next character must be '>'.
134		* And any other characters should raise an ioerror.
135		* But Adobe Acrobat allows CR/LF between ~ and >.
136		* So we allow CR/LF between them. */
137		/* PDF further relaxes the requirements and accepts bare '~'.
138		*/
139	526k	while ((p + i <= rlimit) && (p[i] == 13 \|\| p[i] == 10))
140	1.43k	i++;
141	524k	if (p + i <= rlimit && p[i] != '>') {
142	524k	if (ss->pdf_rules) {
143	1	if (p[i] == 13 \|\| p[i] == 10) {
144	0	if (!last)
145	0	break;
146	1	} else {
147	1	p--;
148	1	}
149	524k	} else {
150	524k	if (p + i == rlimit) {
151	13	if (last)
152	13	status = ERRC;
153	0	else
154	0	p--; /* we'll see the '~' after filling the buffer */
155	13	}
156	524k	break;
157	524k	}
158	524k	}
159	169	finish:
160	169	if (p + i <= rlimit)
161	133	p += i; /* advance to the '>' */
162	36	else
163	36	p = rlimit; /* Can happen if the '>' is missing */
164	169	pw->ptr = q;
165	169	status = a85d_finish(ccount, word, pw);
166	169	q = pw->ptr;
167	169	break;
168	524k	} else { /* syntax error or exception */
169	461	status = ERRC;
170	461	break;
171	461	}
172	6.23M	}
173	531k	pw->ptr = q;
174	531k	if (status == 0 && last) {
175	517	if ((int)(wlimit - q) < ccount - 1)
176	0	status = 1;
177	517	else if (ss->require_eod)
178	511	status = ERRC;
179	6	else
180	6	status = a85d_finish(ccount, word, pw);
181	517	}
182	531k	pr->ptr = p;
183	531k	ss->odd = ccount;
184	531k	ss->word = word;
185	531k	return status;
186	531k	}
187		/* Handle the end of input data. */
188		static int
189		a85d_finish(int ccount, ulong word, stream_cursor_write * pw)
190	175	{
191		/* Assume there is enough room in the output buffer! */
192	175	byte *q = pw->ptr;
193	175	int status = EOFC;
194
195	175	switch (ccount) {
196	36	case 0:
197	36	break;
198	18	case 1: /* syntax error */
199	18	status = ERRC;
200	18	break;
201	46	case 2: /* 1 odd byte */
202	46	word = word * (85L * 85 * 85) + 85L * 85 * 85 - 1L;
203	46	goto o1;
204	40	case 3: /* 2 odd bytes */
205	40	word = word * (85L * 85) + 85L * 85L - 1L;
206	40	goto o2;
207	35	case 4: /* 3 odd bytes */
208	35	word = word * 85L + 84L;
209	35	q[3] = (byte) (word >> 8);
210	75	o2: q[2] = (byte) (word >> 16);
211	121	o1: q[1] = (byte) (word >> 24);
212	121	q += ccount - 1;
213	121	pw->ptr = q;
214	175	}
215	175	return status;
216	175	}
217
218		/* Stream template */
219		const stream_template s_A85D_template = {
220		&st_A85D_state, s_A85D_init, s_A85D_process, 2, 4
221		};