/src/ghostpdl/base/sa85d.c

Source
/* Copyright (C) 2001-2023 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;

            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;
            }
            if ((int)(wlimit - q) < ccount - 1) {
                status = 1;
                p--;
                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: 2026-08-08 08:00

Line	Count	Source
1		/* Copyright (C) 2001-2023 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	544	{
31	544	stream_A85D_state const ss = (stream_A85D_state ) st;
32
33	544	s_A85D_init_inline(ss);
34	544	return 0;
35	544	}
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	500k	{
43	500k	stream_A85D_state const ss = (stream_A85D_state ) st;
44	500k	register const byte *p = pr->ptr;
45	500k	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	500k	const byte rlimit = pr->limit - (last ? 0 : 7); / max EOD len + 1 */
51	500k	const byte *r = max(p, rlimit);
52	500k	byte *wlimit = pw->limit;
53	500k	int ccount = ss->odd;
54	500k	ulong word = ss->word;
55	500k	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	1.14M	while (r < pr->limit) {
60	640k	if (*++r == '~')
61	3.33M	while (r < pr->limit)
62	2.84M	if (*++r == '>') {
63		/* we have both characters of a complete EOD. */
64	404	rlimit = pr->limit; /* go ahead and process everything */
65	404	r = rlimit; /* break out of the while loops */
66	404	break;
67	404	}
68	640k	}
69	5.95M	while (p < rlimit) {
70	5.94M	int ch = *++p;
71	5.94M	uint ccode = ch - '!';
72
73	5.94M	if (ccode < 85) { /* catches ch < '!' as well */
74	5.43M	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	1.08M	if (wlimit - q < 4) {
80	1.29k	p--;
81	1.29k	status = 1;
82	1.29k	break;
83	1.29k	}
84		/* Check for overflow condition, throw ioerror if so */
85	1.08M	if (word >= 0x03030303 && ccode > 0) {
86	152	status = ERRC;
87	152	break;
88	152	}
89	1.08M	word = word * 85 + ccode;
90	1.08M	q[1] = (byte) (word >> 24);
91	1.08M	q[2] = (byte) (word >> 16);
92	1.08M	q[3] = (byte) ((uint) word >> 8);
93	1.08M	q[4] = (byte) word;
94	1.08M	q += 4;
95	1.08M	word = 0;
96	1.08M	ccount = 0;
97	4.34M	} else {
98	4.34M	word = word * 85 + ccode;
99	4.34M	++ccount;
100	4.34M	}
101	5.43M	} else if (ch == 'z' && ccount == 0) {
102	496	if (wlimit - q < 4) {
103	0	p--;
104	0	status = 1;
105	0	break;
106	0	}
107	496	q[1] = q[2] = q[3] = q[4] = 0,
108	496	q += 4;
109	514k	} else if (scan_char_decoder[ch] == ctype_space)
110	514k	DO_NOTHING;
111	494k	else if (ch == '~') {
112	493k	int i = 1;
113
114	493k	rlimit = pr->limit; /* Here we use the real "limit" */
115		/* Handle odd bytes. */
116	493k	if (p == rlimit) {
117	16	if (!last)
118	0	p--;
119	16	else if (ss->pdf_rules)
120	0	goto finish;
121	16	else
122	16	status = ERRC;
123	16	break;
124	16	}
125	493k	if ((int)(wlimit - q) < ccount - 1) {
126	106	status = 1;
127	106	p--;
128	106	break;
129	106	}
130
131		/* According to PLRM 3rd, if the A85 filter encounters '~',
132		* the next character must be '>'.
133		* And any other characters should raise an ioerror.
134		* But Adobe Acrobat allows CR/LF between ~ and >.
135		* So we allow CR/LF between them. */
136		/* PDF further relaxes the requirements and accepts bare '~'.
137		*/
138	495k	while ((p + i <= rlimit) && (p[i] == 13 \|\| p[i] == 10))
139	1.43k	i++;
140	493k	if (p + i <= rlimit && p[i] != '>') {
141	493k	if (ss->pdf_rules) {
142	0	if (p[i] == 13 \|\| p[i] == 10) {
143	0	if (!last)
144	0	break;
145	0	} else {
146	0	p--;
147	0	}
148	493k	} else {
149	493k	if (p + i == rlimit) {
150	11	if (last)
151	11	status = ERRC;
152	0	else
153	0	p--; /* we'll see the '~' after filling the buffer */
154	11	}
155	493k	break;
156	493k	}
157	493k	}
158	150	finish:
159	150	if (p + i <= rlimit)
160	114	p += i; /* advance to the '>' */
161	36	else
162	36	p = rlimit; /* Can happen if the '>' is missing */
163	150	pw->ptr = q;
164	150	status = a85d_finish(ccount, word, pw);
165	150	q = pw->ptr;
166	150	break;
167	493k	} else { /* syntax error or exception */
168	403	status = ERRC;
169	403	break;
170	403	}
171	5.94M	}
172	500k	pw->ptr = q;
173	500k	if (status == 0 && last) {
174	491	if ((int)(wlimit - q) < ccount - 1)
175	0	status = 1;
176	491	else if (ss->require_eod)
177	485	status = ERRC;
178	6	else
179	6	status = a85d_finish(ccount, word, pw);
180	491	}
181	500k	pr->ptr = p;
182	500k	ss->odd = ccount;
183	500k	ss->word = word;
184	500k	return status;
185	500k	}
186		/* Handle the end of input data. */
187		static int
188		a85d_finish(int ccount, ulong word, stream_cursor_write * pw)
189	156	{
190		/* Assume there is enough room in the output buffer! */
191	156	byte *q = pw->ptr;
192	156	int status = EOFC;
193
194	156	switch (ccount) {
195	35	case 0:
196	35	break;
197	18	case 1: /* syntax error */
198	18	status = ERRC;
199	18	break;
200	40	case 2: /* 1 odd byte */
201	40	word = word * (85L * 85 * 85) + 85L * 85 * 85 - 1L;
202	40	goto o1;
203	35	case 3: /* 2 odd bytes */
204	35	word = word * (85L * 85) + 85L * 85L - 1L;
205	35	goto o2;
206	28	case 4: /* 3 odd bytes */
207	28	word = word * 85L + 84L;
208	28	q[3] = (byte) (word >> 8);
209	63	o2: q[2] = (byte) (word >> 16);
210	103	o1: q[1] = (byte) (word >> 24);
211	103	q += ccount - 1;
212	103	pw->ptr = q;
213	156	}
214	156	return status;
215	156	}
216
217		/* Stream template */
218		const stream_template s_A85D_template = {
219		&st_A85D_state, s_A85D_init, s_A85D_process, 2, 4
220		};