[unix-history] / bin / dd / conv.c

/*-
 * Copyright (c) 1991 The Regents of the University of California.
 * All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Keith Muller of the University of California, San Diego and Lance
 * Visser of Convex Computer Corporation.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

#ifndef lint
static char sccsid[] = "@(#)conv.c	5.6 (Berkeley) 4/28/93";
#endif /* not lint */

#include <sys/param.h>

#include <string.h>

#include "dd.h"
#include "extern.h"

/*
 * def --
 * Copy input to output.  Input is buffered until reaches obs, and then
 * output until less than obs remains.  Only a single buffer is used.
 * Worst case buffer calculation is (ibs + obs - 1).
 */
void
def()
{
	register int cnt;
	register u_char *inp, *t;

	if (t = ctab)
		for (inp = in.dbp - (cnt = in.dbrcnt); cnt--; ++inp)
			*inp = t[*inp];

	/* Make the output buffer look right. */
	out.dbp = in.dbp;
	out.dbcnt = in.dbcnt;

	if (in.dbcnt >= out.dbsz) {
		/* If the output buffer is full, write it. */
		dd_out(0);

		/*
		 * Ddout copies the leftover output to the beginning of
		 * the buffer and resets the output buffer.  Reset the
		 * input buffer to match it.
	 	 */
		in.dbp = out.dbp;
		in.dbcnt = out.dbcnt;
	}
}

void
def_close()
{
	/* Just update the count, everything is already in the buffer. */
	if (in.dbcnt)
		out.dbcnt = in.dbcnt;
}

/*
 * Copy variable length newline terminated records with a max size cbsz
 * bytes to output.  Records less than cbs are padded with spaces.
 *
 * max in buffer:  MAX(ibs, cbsz)
 * max out buffer: obs + cbsz
 */
void
block()
{
	static int intrunc;
	register int ch, cnt;
	register u_char *inp, *outp, *t;
	int maxlen;

	/*
	 * Record truncation can cross block boundaries.  If currently in a
	 * truncation state, keep tossing characters until reach a newline.
	 * Start at the beginning of the buffer, as the input buffer is always
	 * left empty.
	 */
	if (intrunc) {
		for (inp = in.db, cnt = in.dbrcnt;
		    cnt && *inp++ != '\n'; --cnt);
		if (!cnt) {
			in.dbcnt = 0;
			in.dbp = in.db;
			return;
		}
		intrunc = 0;
		/* Adjust the input buffer numbers. */
		in.dbcnt = cnt - 1;
		in.dbp = inp + cnt - 1;
	}

	/*
	 * Copy records (max cbsz size chunks) into the output buffer.  The
	 * translation is done as we copy into the output buffer.
	 */
	for (inp = in.dbp - in.dbcnt, outp = out.dbp; in.dbcnt;) {
		maxlen = MIN(cbsz, in.dbcnt);
		if (t = ctab)
			for (cnt = 0;
			    cnt < maxlen && (ch = *inp++) != '\n'; ++cnt)
				*outp++ = t[ch];
		else
			for (cnt = 0;
			    cnt < maxlen && (ch = *inp++) != '\n'; ++cnt)
				*outp++ = ch;
		/*
		 * Check for short record without a newline.  Reassemble the
		 * input block.
		 */
		if (ch != '\n' && in.dbcnt < cbsz) {
			memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
			break;
		}

		/* Adjust the input buffer numbers. */
		in.dbcnt -= cnt;
		if (ch == '\n')
			--in.dbcnt;

		/* Pad short records with spaces. */
		if (cnt < cbsz)
			(void)memset(outp, ctab ? ctab[' '] : ' ', cbsz - cnt);
		else {
			/*
			 * If the next character wouldn't have ended the
			 * block, it's a truncation.
			 */
			if (!in.dbcnt || *inp != '\n')
				++st.trunc;

			/* Toss characters to a newline. */
			for (; in.dbcnt && *inp++ != '\n'; --in.dbcnt);
			if (!in.dbcnt)
				intrunc = 1;
			else
				--in.dbcnt;
		}

		/* Adjust output buffer numbers. */
		out.dbp += cbsz;
		if ((out.dbcnt += cbsz) >= out.dbsz)
			dd_out(0);
		outp = out.dbp;
	}
	in.dbp = in.db + in.dbcnt;
}

void
block_close()
{
	/*
	 * Copy any remaining data into the output buffer and pad to a record.
	 * Don't worry about truncation or translation, the input buffer is
	 * always empty when truncating, and no characters have been added for
	 * translation.  The bottom line is that anything left in the input
	 * buffer is a truncated record.  Anything left in the output buffer
	 * just wasn't big enough.
	 */
	if (in.dbcnt) {
		++st.trunc;
		memmove(out.dbp, in.dbp - in.dbcnt, in.dbcnt);
		(void)memset(out.dbp + in.dbcnt,
		    ctab ? ctab[' '] : ' ', cbsz - in.dbcnt);
		out.dbcnt += cbsz;
	}
}

/*
 * Convert fixed length (cbsz) records to variable length.  Deletes any
 * trailing blanks and appends a newline.
 *
 * max in buffer:  MAX(ibs, cbsz) + cbsz
 * max out buffer: obs + cbsz
 */
void
unblock()
{
	register int cnt;
	register u_char *inp, *t;

	/* Translation and case conversion. */
	if (t = ctab)
		for (cnt = in.dbrcnt, inp = in.dbp; cnt--;)
			*--inp = t[*inp];
	/*
	 * Copy records (max cbsz size chunks) into the output buffer.  The
	 * translation has to already be done or we might not recognize the
	 * spaces.
	 */
	for (inp = in.db; in.dbcnt >= cbsz; inp += cbsz, in.dbcnt -= cbsz) {
		for (t = inp + cbsz - 1; t >= inp && *t == ' '; --t);
		if (t >= inp) {
			cnt = t - inp + 1;
			memmove(out.dbp, inp, cnt);
			out.dbp += cnt;
			out.dbcnt += cnt;
		}
		++out.dbcnt;
		*out.dbp++ = '\n';
		if (out.dbcnt >= out.dbsz)
			dd_out(0);
	}
	if (in.dbcnt)
		memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
	in.dbp = in.db + in.dbcnt;
}

void
unblock_close()
{
	register int cnt;
	register u_char *t;

	if (in.dbcnt) {
		warn("%s: short input record", in.name);
		for (t = in.db + in.dbcnt - 1; t >= in.db && *t == ' '; --t);
		if (t >= in.db) {
			cnt = t - in.db + 1;
			memmove(out.dbp, in.db, cnt);
			out.dbp += cnt;
			out.dbcnt += cnt;
		}
		++out.dbcnt;
		*out.dbp++ = '\n';
	}
}
Commit	Line	Data
cb955067 NW	1	/*-
	2	* Copyright (c) 1991 The Regents of the University of California.
	3	* All rights reserved.
	4	*
	5	* This code is derived from software contributed to Berkeley by
	6	* Keith Muller of the University of California, San Diego and Lance
	7	* Visser of Convex Computer Corporation.
	8	*
	9	* Redistribution and use in source and binary forms, with or without
	10	* modification, are permitted provided that the following conditions
	11	* are met:
	12	* 1. Redistributions of source code must retain the above copyright
	13	* notice, this list of conditions and the following disclaimer.
	14	* 2. Redistributions in binary form must reproduce the above copyright
	15	* notice, this list of conditions and the following disclaimer in the
	16	* documentation and/or other materials provided with the distribution.
	17	* 3. All advertising materials mentioning features or use of this software
	18	* must display the following acknowledgement:
	19	* This product includes software developed by the University of
	20	* California, Berkeley and its contributors.
	21	* 4. Neither the name of the University nor the names of its contributors
	22	* may be used to endorse or promote products derived from this software
	23	* without specific prior written permission.
	24	*
	25	* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
	26	* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
	27	* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
	28	* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
	29	* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
	30	* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
	31	* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
	32	* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
	33	* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
	34	* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
	35	* SUCH DAMAGE.
	36	*/
	37
	38	#ifndef lint
	39	static char sccsid[] = "@(#)conv.c 5.6 (Berkeley) 4/28/93";
	40	#endif /* not lint */
	41
	42	#include <sys/param.h>
	43
	44	#include <string.h>
	45
	46	#include "dd.h"
	47	#include "extern.h"
	48
	49	/*
	50	* def --
	51	* Copy input to output. Input is buffered until reaches obs, and then
	52	* output until less than obs remains. Only a single buffer is used.
	53	* Worst case buffer calculation is (ibs + obs - 1).
	54	*/
	55	void
	56	def()
	57	{
	58	register int cnt;
	59	register u_char inp, t;
	60
	61	if (t = ctab)
	62	for (inp = in.dbp - (cnt = in.dbrcnt); cnt--; ++inp)
	63	inp = t[inp];
	64
65	/* Make the output buffer look right. */
66	out.dbp = in.dbp;
67	out.dbcnt = in.dbcnt;
68
69	if (in.dbcnt >= out.dbsz) {
70	/* If the output buffer is full, write it. */
71	dd_out(0);
72
73	/*
74	* Ddout copies the leftover output to the beginning of
75	* the buffer and resets the output buffer. Reset the
76	* input buffer to match it.
77	*/
78	in.dbp = out.dbp;
79	in.dbcnt = out.dbcnt;
80	}
81	}
82
83	void
84	def_close()
85	{
86	/* Just update the count, everything is already in the buffer. */
87	if (in.dbcnt)
88	out.dbcnt = in.dbcnt;
89	}
90
91	/*
92	* Copy variable length newline terminated records with a max size cbsz
93	* bytes to output. Records less than cbs are padded with spaces.
94	*
95	* max in buffer: MAX(ibs, cbsz)
96	* max out buffer: obs + cbsz
97	*/
98	void
99	block()
100	{
101	static int intrunc;
102	register int ch, cnt;
103	register u_char inp, outp, *t;
104	int maxlen;
105
106	/*
107	* Record truncation can cross block boundaries. If currently in a
108	* truncation state, keep tossing characters until reach a newline.
109	* Start at the beginning of the buffer, as the input buffer is always
110	* left empty.
111	*/
112	if (intrunc) {
113	for (inp = in.db, cnt = in.dbrcnt;
114	cnt && *inp++ != '\n'; --cnt);
115	if (!cnt) {
116	in.dbcnt = 0;
117	in.dbp = in.db;
118	return;
119	}
120	intrunc = 0;
121	/* Adjust the input buffer numbers. */
122	in.dbcnt = cnt - 1;
123	in.dbp = inp + cnt - 1;
124	}
125
126	/*
127	* Copy records (max cbsz size chunks) into the output buffer. The
128	* translation is done as we copy into the output buffer.
129	*/
130	for (inp = in.dbp - in.dbcnt, outp = out.dbp; in.dbcnt;) {
131	maxlen = MIN(cbsz, in.dbcnt);
132	if (t = ctab)
133	for (cnt = 0;
134	cnt < maxlen && (ch = *inp++) != '\n'; ++cnt)
135	*outp++ = t[ch];
136	else
137	for (cnt = 0;
138	cnt < maxlen && (ch = *inp++) != '\n'; ++cnt)
139	*outp++ = ch;
140	/*
141	* Check for short record without a newline. Reassemble the
142	* input block.
143	*/
144	if (ch != '\n' && in.dbcnt < cbsz) {
145	memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
146	break;
147	}
148
149	/* Adjust the input buffer numbers. */
150	in.dbcnt -= cnt;
151	if (ch == '\n')
152	--in.dbcnt;
153
154	/* Pad short records with spaces. */
155	if (cnt < cbsz)
156	(void)memset(outp, ctab ? ctab[' '] : ' ', cbsz - cnt);
157	else {
158	/*
159	* If the next character wouldn't have ended the
160	* block, it's a truncation.
161	*/
162	if (!in.dbcnt \|\| *inp != '\n')
163	++st.trunc;
164
165	/* Toss characters to a newline. */
166	for (; in.dbcnt && *inp++ != '\n'; --in.dbcnt);
167	if (!in.dbcnt)
168	intrunc = 1;
169	else
170	--in.dbcnt;
171	}
172
173	/* Adjust output buffer numbers. */
174	out.dbp += cbsz;
175	if ((out.dbcnt += cbsz) >= out.dbsz)
176	dd_out(0);
177	outp = out.dbp;
178	}
179	in.dbp = in.db + in.dbcnt;
180	}
181
182	void
183	block_close()
184	{
185	/*
186	* Copy any remaining data into the output buffer and pad to a record.
187	* Don't worry about truncation or translation, the input buffer is
188	* always empty when truncating, and no characters have been added for
189	* translation. The bottom line is that anything left in the input
190	* buffer is a truncated record. Anything left in the output buffer
191	* just wasn't big enough.
192	*/
193	if (in.dbcnt) {
194	++st.trunc;
195	memmove(out.dbp, in.dbp - in.dbcnt, in.dbcnt);
196	(void)memset(out.dbp + in.dbcnt,
197	ctab ? ctab[' '] : ' ', cbsz - in.dbcnt);
198	out.dbcnt += cbsz;
199	}
200	}
201
202	/*
203	* Convert fixed length (cbsz) records to variable length. Deletes any
204	* trailing blanks and appends a newline.
205	*
206	* max in buffer: MAX(ibs, cbsz) + cbsz
207	* max out buffer: obs + cbsz
208	*/
209	void
210	unblock()
211	{
212	register int cnt;
213	register u_char inp, t;
214
215	/* Translation and case conversion. */
216	if (t = ctab)
217	for (cnt = in.dbrcnt, inp = in.dbp; cnt--;)
218	--inp = t[inp];
219	/*
220	* Copy records (max cbsz size chunks) into the output buffer. The
221	* translation has to already be done or we might not recognize the
222	* spaces.
223	*/
224	for (inp = in.db; in.dbcnt >= cbsz; inp += cbsz, in.dbcnt -= cbsz) {
225	for (t = inp + cbsz - 1; t >= inp && *t == ' '; --t);
226	if (t >= inp) {
227	cnt = t - inp + 1;
228	memmove(out.dbp, inp, cnt);
229	out.dbp += cnt;
230	out.dbcnt += cnt;
231	}
232	++out.dbcnt;
233	*out.dbp++ = '\n';
234	if (out.dbcnt >= out.dbsz)
235	dd_out(0);
236	}
237	if (in.dbcnt)
238	memmove(in.db, in.dbp - in.dbcnt, in.dbcnt);
239	in.dbp = in.db + in.dbcnt;
240	}
241
242	void
243	unblock_close()
244	{
245	register int cnt;
246	register u_char *t;
247
248	if (in.dbcnt) {
249	warn("%s: short input record", in.name);
250	for (t = in.db + in.dbcnt - 1; t >= in.db && *t == ' '; --t);
251	if (t >= in.db) {
252	cnt = t - in.db + 1;
253	memmove(out.dbp, in.db, cnt);
254	out.dbp += cnt;
255	out.dbcnt += cnt;
256	}
257	++out.dbcnt;
258	*out.dbp++ = '\n';
259	}
260	}