=================================================================== RCS file: /cvs/mandoc/mdoc_macro.c,v retrieving revision 1.61 retrieving revision 1.71 diff -u -p -r1.61 -r1.71 --- mandoc/mdoc_macro.c 2010/05/13 11:34:45 1.61 +++ mandoc/mdoc_macro.c 2010/05/30 21:28:30 1.71 @@ -1,4 +1,4 @@ -/* $Id: mdoc_macro.c,v 1.61 2010/05/13 11:34:45 kristaps Exp $ */ +/* $Id: mdoc_macro.c,v 1.71 2010/05/30 21:28:30 kristaps Exp $ */ /* * Copyright (c) 2008, 2009 Kristaps Dzonsons * @@ -25,7 +25,9 @@ #include #include +#include "mandoc.h" #include "libmdoc.h" +#include "libmandoc.h" enum rew { REWIND_REWIND, @@ -48,7 +50,7 @@ static int append_delims(struct mdoc *, static enum mdoct lookup(enum mdoct, const char *); static enum mdoct lookup_raw(const char *); static int phrase(struct mdoc *, int, int, - char *, enum margserr, int); + char *, enum margserr); static enum mdoct rew_alt(enum mdoct); static int rew_dobreak(enum mdoct, const struct mdoc_node *); @@ -169,7 +171,7 @@ const struct mdoc_macro __mdoc_macros[MDOC_MAX] = { { in_line_eoln, 0 }, /* Hf */ { obsolete, 0 }, /* Fr */ { in_line_eoln, 0 }, /* Ud */ - { in_line_eoln, 0 }, /* Lb */ + { in_line, 0 }, /* Lb */ { in_line_eoln, 0 }, /* Lp */ { in_line, MDOC_CALLABLE | MDOC_PARSED }, /* Lk */ { in_line, MDOC_CALLABLE | MDOC_PARSED }, /* Mt */ @@ -194,6 +196,7 @@ swarn(struct mdoc *mdoc, enum mdoc_type type, int line, int pos, const struct mdoc_node *p) { const char *n, *t, *tt; + int rc; n = t = ""; tt = "block"; @@ -226,13 +229,11 @@ swarn(struct mdoc *mdoc, enum mdoc_type type, break; } - if ( ! (MDOC_IGN_SCOPE & mdoc->pflags)) - return(mdoc_verr(mdoc, line, pos, - "%s scope breaks %s scope of %s", - tt, t, n)); - return(mdoc_vwarn(mdoc, line, pos, - "%s scope breaks %s scope of %s", - tt, t, n)); + rc = mdoc_vmsg(mdoc, MANDOCERR_SCOPE, line, pos, + "%s scope breaks %s of %s", tt, t, n); + + /* FIXME: logic should be in driver. */ + return(MDOC_IGN_SCOPE & mdoc->pflags ? rc : 0); } @@ -255,7 +256,8 @@ mdoc_macroend(struct mdoc *m) continue; if ( ! (MDOC_EXPLICIT & mdoc_macros[n->tok].flags)) continue; - return(mdoc_nerr(m, n, EOPEN)); + mdoc_nmsg(m, n, MANDOCERR_SYNTSCOPE); + return(0); } /* Rewind to the first. */ @@ -587,7 +589,9 @@ rew_sub(enum mdoc_type t, struct mdoc *m, return(1); if ( ! (MDOC_EXPLICIT & mdoc_macros[tok].flags)) return(1); - return(mdoc_perr(m, line, ppos, ENOCTX)); + /* FIXME: shouldn't raise an error */ + mdoc_pmsg(m, line, ppos, MANDOCERR_SYNTNOSCOPE); + return(0); } if (REWIND_REWIND == c) break; @@ -621,26 +625,41 @@ rew_sub(enum mdoc_type t, struct mdoc *m, static int -append_delims(struct mdoc *mdoc, int line, int *pos, char *buf) +append_delims(struct mdoc *m, int line, int *pos, char *buf) { - int lastarg; + int la; enum margserr ac; char *p; - if (0 == buf[*pos]) + if ('\0' == buf[*pos]) return(1); for (;;) { - lastarg = *pos; - ac = mdoc_zargs(mdoc, line, pos, buf, ARGS_NOWARN, &p); + la = *pos; + ac = mdoc_zargs(m, line, pos, buf, ARGS_NOWARN, &p); if (ARGS_ERROR == ac) return(0); else if (ARGS_EOLN == ac) break; - assert(mdoc_isdelim(p)); - if ( ! mdoc_word_alloc(mdoc, line, lastarg, p)) + + assert(DELIM_NONE != mdoc_isdelim(p)); + if ( ! mdoc_word_alloc(m, line, la, p)) return(0); + + /* + * If we encounter end-of-sentence symbols, then trigger + * the double-space. + * + * XXX: it's easy to allow this to propogate outward to + * the last symbol, such that `. )' will cause the + * correct double-spacing. However, (1) groff isn't + * smart enough to do this and (2) it would require + * knowing which symbols break this behaviour, for + * example, `. ;' shouldn't propogate the double-space. + */ + if (mandoc_eos(p, strlen(p))) + m->last->flags |= MDOC_EOS; } return(1); @@ -670,8 +689,9 @@ blk_exp_close(MACRO_PROT_ARGS) } if ( ! (MDOC_CALLABLE & mdoc_macros[tok].flags)) { + /* FIXME: do this in validate */ if (buf[*pos]) - if ( ! mdoc_pwarn(m, line, ppos, ENOLINE)) + if ( ! mdoc_pmsg(m, line, ppos, MANDOCERR_ARGSLOST)) return(0); if ( ! rew_sub(MDOC_BODY, m, tok, line, ppos)) @@ -734,10 +754,11 @@ blk_exp_close(MACRO_PROT_ARGS) static int in_line(MACRO_PROT_ARGS) { - int la, lastpunct, cnt, d, nc, nl; + int la, scope, cnt, nc, nl; enum margverr av; enum mdoct ntok; enum margserr ac; + enum mdelim d; struct mdoc_arg *arg; char *p; @@ -784,7 +805,7 @@ in_line(MACRO_PROT_ARGS) return(0); } - for (cnt = 0, lastpunct = 1;; ) { + for (cnt = scope = 0;; ) { la = *pos; ac = mdoc_args(m, line, pos, buf, tok, &p); @@ -805,7 +826,7 @@ in_line(MACRO_PROT_ARGS) */ if (MDOC_MAX != ntok) { - if (0 == lastpunct && ! rew_elem(m, tok)) + if (scope && ! rew_elem(m, tok)) return(0); if (nc && 0 == cnt) { if ( ! mdoc_elem_alloc(m, line, ppos, tok, arg)) @@ -814,7 +835,7 @@ in_line(MACRO_PROT_ARGS) return(0); } else if ( ! nc && 0 == cnt) { mdoc_argv_free(arg); - if ( ! mdoc_pwarn(m, line, ppos, EIGNE)) + if ( ! mdoc_pmsg(m, line, ppos, MANDOCERR_MACROEMPTY)) return(0); } if ( ! mdoc_macro(m, ntok, line, la, pos, buf)) @@ -830,19 +851,40 @@ in_line(MACRO_PROT_ARGS) * the word. */ - d = ARGS_QWORD == ac ? 0 : mdoc_isdelim(p); + d = ARGS_QWORD == ac ? DELIM_NONE : mdoc_isdelim(p); - if (ARGS_QWORD != ac && d) { - if (0 == lastpunct && ! rew_elem(m, tok)) + if (DELIM_NONE != d) { + /* + * If we encounter closing punctuation, no word + * has been omitted, no scope is open, and we're + * allowed to have an empty element, then start + * a new scope. `Ar', `Fl', and `Li', only do + * this once per invocation. There may be more + * of these (all of them?). + */ + if (0 == cnt && (nc || MDOC_Li == tok) && + DELIM_CLOSE == d && ! scope) { + if ( ! mdoc_elem_alloc(m, line, ppos, tok, arg)) + return(0); + if (MDOC_Ar == tok || MDOC_Li == tok || + MDOC_Fl == tok) + cnt++; + scope = 1; + } + /* + * Close out our scope, if one is open, before + * any punctuation. + */ + if (scope && ! rew_elem(m, tok)) return(0); - lastpunct = 1; - } else if (lastpunct) { + scope = 0; + } else if ( ! scope) { if ( ! mdoc_elem_alloc(m, line, ppos, tok, arg)) return(0); - lastpunct = 0; + scope = 1; } - if ( ! d) + if (DELIM_NONE == d) cnt++; if ( ! mdoc_word_alloc(m, line, la, p)) return(0); @@ -852,14 +894,14 @@ in_line(MACRO_PROT_ARGS) * word so that the `-' can be added to each one without * having to parse out spaces. */ - if (0 == lastpunct && MDOC_Fl == tok) { + if (scope && MDOC_Fl == tok) { if ( ! rew_elem(m, tok)) return(0); - lastpunct = 1; + scope = 0; } } - if (0 == lastpunct && ! rew_elem(m, tok)) + if (scope && ! rew_elem(m, tok)) return(0); /* @@ -875,7 +917,7 @@ in_line(MACRO_PROT_ARGS) return(0); } else if ( ! nc && 0 == cnt) { mdoc_argv_free(arg); - if ( ! mdoc_pwarn(m, line, ppos, EIGNE)) + if ( ! mdoc_pmsg(m, line, ppos, MANDOCERR_MACROEMPTY)) return(0); } @@ -888,7 +930,7 @@ in_line(MACRO_PROT_ARGS) static int blk_full(MACRO_PROT_ARGS) { - int la, pcnt; + int la, nl; struct mdoc_arg *arg; struct mdoc_node *head; /* save of head macro */ struct mdoc_node *body; /* save of body macro */ @@ -900,6 +942,8 @@ blk_full(MACRO_PROT_ARGS) enum margverr av; char *p; + nl = MDOC_NEWLINE & m->flags; + /* Close out prior implicit scope. */ if ( ! (MDOC_EXPLICIT & mdoc_macros[tok].flags)) { @@ -958,8 +1002,9 @@ blk_full(MACRO_PROT_ARGS) } ac = ARGS_ERROR; + lac = ARGS_PHRASE; - for (pcnt = 0; ; ) { + for ( ; ; ) { la = *pos; lac = ac; ac = mdoc_args(m, line, pos, buf, tok, &p); @@ -972,11 +1017,11 @@ blk_full(MACRO_PROT_ARGS) /* Don't emit leading punct. for phrases. */ if (NULL == head && + ARGS_PEND != ac && ARGS_PHRASE != ac && ARGS_PPHRASE != ac && - ARGS_PEND != ac && ARGS_QWORD != ac && - 1 == mdoc_isdelim(p)) { + DELIM_OPEN == mdoc_isdelim(p)) { if ( ! mdoc_word_alloc(m, line, la, p)) return(0); continue; @@ -985,30 +1030,28 @@ blk_full(MACRO_PROT_ARGS) /* Always re-open head for phrases. */ if (NULL == head || + ARGS_PEND == ac || ARGS_PHRASE == ac || - ARGS_PEND == ac || ARGS_PPHRASE == ac) { if ( ! mdoc_head_alloc(m, line, ppos, tok)) return(0); head = m->last; } - if (ARGS_PHRASE == ac || - ARGS_PEND == ac || - ARGS_PPHRASE == ac) { - /* - * Special treatment for the last phrase. A - * prior ARGS_PHRASE gets is handled as a - * regular ARGS_PHRASE, but a prior ARGS_PPHRASE - * has special handling. - */ - if (ARGS_PEND == ac && ARGS_ERROR == lac) - ac = ARGS_PHRASE; - else if (ARGS_PEND == ac && ARGS_PHRASE == lac) - ac = ARGS_PHRASE; + if (ARGS_PHRASE == ac || ARGS_PPHRASE == ac) { + if (ARGS_PPHRASE == ac) + m->flags |= MDOC_PPHRASE; + if (ARGS_PEND == ac && ARGS_PPHRASE == lac) + m->flags |= MDOC_PPHRASE; - if ( ! phrase(m, line, la, buf, ac, pcnt++)) + if (ARGS_PEND == ac) { + if ( ! phrase(m, line, la, buf, lac)) + return(0); + } else if ( ! phrase(m, line, la, buf, ac)) return(0); + + m->flags &= ~MDOC_PPHRASE; + if ( ! rew_sub(MDOC_HEAD, m, tok, line, ppos)) return(0); continue; @@ -1033,7 +1076,7 @@ blk_full(MACRO_PROT_ARGS) head = m->last; } - if (1 == ppos && ! append_delims(m, line, pos, buf)) + if (nl && ! append_delims(m, line, pos, buf)) return(0); /* If we've already opened our body, exit now. */ @@ -1073,7 +1116,7 @@ blk_full(MACRO_PROT_ARGS) static int blk_part_imp(MACRO_PROT_ARGS) { - int la; + int la, nl; enum mdoct ntok; enum margserr ac; char *p; @@ -1081,6 +1124,8 @@ blk_part_imp(MACRO_PROT_ARGS) struct mdoc_node *body; /* saved body context */ struct mdoc_node *n; + nl = MDOC_NEWLINE & m->flags; + /* * A macro that spans to the end of the line. This is generally * (but not necessarily) called as the first macro. The block @@ -1118,7 +1163,7 @@ blk_part_imp(MACRO_PROT_ARGS) break; if (NULL == body && ARGS_QWORD != ac && - 1 == mdoc_isdelim(p)) { + DELIM_OPEN == mdoc_isdelim(p)) { if ( ! mdoc_word_alloc(m, line, la, p)) return(0); continue; @@ -1151,17 +1196,38 @@ blk_part_imp(MACRO_PROT_ARGS) body = m->last; } + for (n = body->child; n && n->next; n = n->next) + /* Do nothing. */ ; + /* + * End of sentence spacing: if the last node is a text node and + * has a trailing period, then mark it as being end-of-sentence. + */ + + if (n && MDOC_TEXT == n->type && n->string) + if (mandoc_eos(n->string, strlen(n->string))) + n->flags |= MDOC_EOS; + + /* Up-propogate the end-of-space flag. */ + + if (n && (MDOC_EOS & n->flags)) { + body->flags |= MDOC_EOS; + body->parent->flags |= MDOC_EOS; + } + + /* * If we can't rewind to our body, then our scope has already * been closed by another macro (like `Oc' closing `Op'). This * is ugly behaviour nodding its head to OpenBSD's overwhelming * crufty use of `Op' breakage. + * + * FIXME - this should be ifdef'd OpenBSD? */ for (n = m->last; n; n = n->parent) if (body == n) break; - if (NULL == n && ! mdoc_nwarn(m, body, EIMPBRK)) + if (NULL == n && ! mdoc_nmsg(m, body, MANDOCERR_SCOPE)) return(0); if (n && ! rew_last(m, body)) @@ -1169,7 +1235,7 @@ blk_part_imp(MACRO_PROT_ARGS) /* Standard appending of delimiters. */ - if (1 == ppos && ! append_delims(m, line, pos, buf)) + if (nl && ! append_delims(m, line, pos, buf)) return(0); /* Rewind scope, if applicable. */ @@ -1216,7 +1282,7 @@ blk_part_exp(MACRO_PROT_ARGS) /* Flush out leading punctuation. */ if (NULL == head && ARGS_QWORD != ac && - 1 == mdoc_isdelim(p)) { + DELIM_OPEN == mdoc_isdelim(p)) { assert(NULL == body); if ( ! mdoc_word_alloc(m, line, la, p)) return(0); @@ -1361,7 +1427,7 @@ in_line_argn(MACRO_PROT_ARGS) if ( ! (MDOC_IGNDELIM & mdoc_macros[tok].flags) && ARGS_QWORD != ac && - 0 == j && 1 == mdoc_isdelim(p)) { + 0 == j && DELIM_OPEN == mdoc_isdelim(p)) { if ( ! mdoc_word_alloc(m, line, la, p)) return(0); continue; @@ -1389,7 +1455,8 @@ in_line_argn(MACRO_PROT_ARGS) if ( ! (MDOC_IGNDELIM & mdoc_macros[tok].flags) && ARGS_QWORD != ac && - ! flushed && mdoc_isdelim(p)) { + ! flushed && + DELIM_NONE != mdoc_isdelim(p)) { if ( ! rew_elem(m, tok)) return(0); flushed = 1; @@ -1526,7 +1593,7 @@ static int obsolete(MACRO_PROT_ARGS) { - return(mdoc_pwarn(m, line, ppos, EOBS)); + return(mdoc_pmsg(m, line, ppos, MANDOCERR_MACROOBS)); } @@ -1536,25 +1603,18 @@ obsolete(MACRO_PROT_ARGS) * macro is encountered. */ static int -phrase(struct mdoc *m, int line, int ppos, char *buf, - enum margserr ac, int count) +phrase(struct mdoc *m, int line, int ppos, char *buf, enum margserr ac) { int la, pos; enum margserr aac; enum mdoct ntok; char *p; - assert(ARGS_PHRASE == ac || - ARGS_PEND == ac || - ARGS_PPHRASE == ac); + assert(ARGS_PHRASE == ac || ARGS_PPHRASE == ac); - if (count && ARGS_PPHRASE == ac) - return(mdoc_word_alloc(m, line, ppos, &buf[ppos])); - for (pos = ppos; ; ) { la = pos; - /* Note: no calling context! */ aac = mdoc_zargs(m, line, &pos, buf, 0, &p); if (ARGS_ERROR == aac) @@ -1562,8 +1622,7 @@ phrase(struct mdoc *m, int line, int ppos, char *buf, if (ARGS_EOLN == aac) break; - ntok = ARGS_QWORD == aac || ARGS_PEND == ac ? - MDOC_MAX : lookup_raw(p); + ntok = ARGS_QWORD == aac ? MDOC_MAX : lookup_raw(p); if (MDOC_MAX == ntok) { if ( ! mdoc_word_alloc(m, line, la, p))