aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/out.c
diff options
context:
space:
mode:
authorKristaps Dzonsons <kristaps@bsd.lv>2011-04-09 15:29:40 +0000
committerKristaps Dzonsons <kristaps@bsd.lv>2011-04-09 15:29:40 +0000
commitdc6820cf87c36506f7d235493e75c1520231e9d9 (patch)
treee5c60975fd48bf07a47693f981a0ff9991db03b9 /out.c
parent0383763dbd62d52405be4dc65ae9aaff035c8f79 (diff)
downloadmandoc-dc6820cf87c36506f7d235493e75c1520231e9d9.tar.gz
mandoc-dc6820cf87c36506f7d235493e75c1520231e9d9.tar.zst
mandoc-dc6820cf87c36506f7d235493e75c1520231e9d9.zip
Remove a2roffdeco() and mandoc_special() functions and replace them with
a public (mandoc.h) function mandoc_escape(), which merges the functionality of both prior functions. Reason: code duplication. The a2roffdeco() and mandoc_special() functions were pretty much the same thing and both quite complex. This allows one function to receive improvements in (e.g.) subexpression handling and performance, instead of having to replicate functionality. As such, the mandoc_escape() function already handles a superset of the escapes handled in previous versions and has improvements in performance (using strcspn(), for example) and reliable handling of subexpressions. This code Works For Me, but may need work to catch any regressions. Since the benefits are great (leaner code, simpler API), I'd rather have it in-tree than floating as a patch.
Diffstat (limited to 'out.c')
-rw-r--r--out.c239
1 files changed, 1 insertions, 238 deletions
diff --git a/out.c b/out.c
index eb303d51..225d4639 100644
--- a/out.c
+++ b/out.c
@@ -1,4 +1,4 @@
-/* $Id: out.c,v 1.39 2011/03/17 08:49:34 kristaps Exp $ */
+/* $Id: out.c,v 1.40 2011/04/09 15:29:40 kristaps Exp $ */
/*
* Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
* Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org>
@@ -174,243 +174,6 @@ time2a(time_t t, char *dst, size_t sz)
(void)strftime(p, sz, "%Y", &tm);
}
-
-int
-a2roffdeco(enum roffdeco *d, const char **word, size_t *sz)
-{
- int i, j, lim;
- char term, c;
- const char *wp;
- enum roffdeco dd;
-
- *d = DECO_NONE;
- lim = i = 0;
- term = '\0';
- wp = *word;
-
- switch ((c = wp[i++])) {
- case ('('):
- *d = DECO_SPECIAL;
- lim = 2;
- break;
- case ('F'):
- /* FALLTHROUGH */
- case ('f'):
- *d = 'F' == c ? DECO_FFONT : DECO_FONT;
-
- switch (wp[i++]) {
- case ('('):
- lim = 2;
- break;
- case ('['):
- term = ']';
- break;
- case ('3'):
- /* FALLTHROUGH */
- case ('B'):
- *d = DECO_BOLD;
- return(i);
- case ('2'):
- /* FALLTHROUGH */
- case ('I'):
- *d = DECO_ITALIC;
- return(i);
- case ('P'):
- *d = DECO_PREVIOUS;
- return(i);
- case ('1'):
- /* FALLTHROUGH */
- case ('R'):
- *d = DECO_ROMAN;
- return(i);
- default:
- i--;
- lim = 1;
- break;
- }
- break;
- case ('k'):
- /* FALLTHROUGH */
- case ('M'):
- /* FALLTHROUGH */
- case ('m'):
- /* FALLTHROUGH */
- case ('*'):
- if ('*' == c)
- *d = DECO_RESERVED;
-
- switch (wp[i++]) {
- case ('('):
- lim = 2;
- break;
- case ('['):
- term = ']';
- break;
- default:
- i--;
- lim = 1;
- break;
- }
- break;
-
- case ('N'):
-
- /*
- * Sequence of characters: backslash, 'N' (i = 0),
- * starting delimiter (i = 1), character number (i = 2).
- */
-
- *word = wp + 2;
- *sz = 0;
-
- /*
- * Cannot use a digit as a starting delimiter;
- * but skip the digit anyway.
- */
-
- if (isdigit((int)wp[1]))
- return(2);
-
- /*
- * Any non-digit terminates the character number.
- * That is, the terminating delimiter need not
- * match the starting delimiter.
- */
-
- for (i = 2; isdigit((int)wp[i]); i++)
- (*sz)++;
-
- /*
- * This is only a numbered character
- * if the character number has at least one digit.
- */
-
- if (*sz)
- *d = DECO_NUMBERED;
-
- /*
- * Skip the terminating delimiter, even if it does not
- * match, and even if there is no character number.
- */
-
- return(++i);
-
- case ('h'):
- /* FALLTHROUGH */
- case ('v'):
- /* FALLTHROUGH */
- case ('s'):
- j = 0;
- if ('+' == wp[i] || '-' == wp[i]) {
- i++;
- j = 1;
- }
-
- switch (wp[i++]) {
- case ('('):
- lim = 2;
- break;
- case ('['):
- term = ']';
- break;
- case ('\''):
- term = '\'';
- break;
- case ('0'):
- j = 1;
- /* FALLTHROUGH */
- default:
- i--;
- lim = 1;
- break;
- }
-
- if ('+' == wp[i] || '-' == wp[i]) {
- if (j)
- return(i);
- i++;
- }
-
- /* Handle embedded numerical subexp or escape. */
-
- if ('(' == wp[i]) {
- while (wp[i] && ')' != wp[i])
- if ('\\' == wp[i++]) {
- /* Handle embedded escape. */
- *word = &wp[i];
- i += a2roffdeco(&dd, word, sz);
- }
-
- if (')' == wp[i++])
- break;
-
- *d = DECO_NONE;
- return(i - 1);
- } else if ('\\' == wp[i]) {
- *word = &wp[++i];
- i += a2roffdeco(&dd, word, sz);
- }
-
- break;
- case ('['):
- *d = DECO_SPECIAL;
- term = ']';
- break;
- case ('c'):
- *d = DECO_NOSPACE;
- return(i);
- case ('z'):
- *d = DECO_NONE;
- if ('\\' == wp[i]) {
- *word = &wp[++i];
- return(i + a2roffdeco(&dd, word, sz));
- } else
- lim = 1;
- break;
- case ('o'):
- /* FALLTHROUGH */
- case ('w'):
- if ('\'' == wp[i++]) {
- term = '\'';
- break;
- }
- /* FALLTHROUGH */
- default:
- *d = DECO_SSPECIAL;
- i--;
- lim = 1;
- break;
- }
-
- assert(term || lim);
- *word = &wp[i];
-
- if (term) {
- j = i;
- while (wp[i] && wp[i] != term)
- i++;
- if ('\0' == wp[i]) {
- *d = DECO_NONE;
- return(i);
- }
-
- assert(i >= j);
- *sz = (size_t)(i - j);
-
- return(i + 1);
- }
-
- assert(lim > 0);
- *sz = (size_t)lim;
-
- for (j = 0; wp[i] && j < lim; j++)
- i++;
- if (j < lim)
- *d = DECO_NONE;
-
- return(i);
-}
-
/*
* Calculate the abstract widths and decimal positions of columns in a
* table. This routine allocates the columns structures then runs over