From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from krisdoz.my.domain (schwarze@localhost [127.0.0.1]) by krisdoz.my.domain (8.14.5/8.14.5) with ESMTP id s9T0HhoS028234 for ; Tue, 28 Oct 2014 20:17:43 -0400 (EDT) Received: (from schwarze@localhost) by krisdoz.my.domain (8.14.5/8.14.3/Submit) id s9T0Hhia030024; Tue, 28 Oct 2014 20:17:43 -0400 (EDT) Date: Tue, 28 Oct 2014 20:17:43 -0400 (EDT) Message-Id: <201410290017.s9T0Hhia030024@krisdoz.my.domain> X-Mailinglist: mdocml-source Reply-To: source@mdocml.bsd.lv MIME-Version: 1.0 From: schwarze@mdocml.bsd.lv To: source@mdocml.bsd.lv Subject: mdocml: In terminal output, unify handling of Unicode and numbered X-Mailer: activitymail 1.26, http://search.cpan.org/dist/activitymail/ Content-Type: text/plain; charset=utf-8 Log Message: ----------- In terminal output, unify handling of Unicode and numbered character escape sequences just like it was earlier implemented for -Thtml. Do not let control characters other than ASCII 9 (horizontal tab) propagate to the output, even though groff allows them; but that really doesn't look like a great idea. Let mchars_num2char() return int such that we can distinguish invalid \N syntax from \N'0'. This also reduces the danger of signed char issues popping up. Modified Files: -------------- mdocml: chars.c html.c mandoc.h term.c Revision Data ------------- Index: term.c =================================================================== RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/term.c,v retrieving revision 1.232 retrieving revision 1.233 diff -Lterm.c -Lterm.c -u -p -r1.232 -r1.233 --- term.c +++ term.c @@ -391,7 +391,6 @@ term_word(struct termp *p, const char *w { const char nbrsp[2] = { ASCII_NBRSP, 0 }; const char *seq, *cp; - char c; int sz, uc; size_t ssz; enum mandoc_esc esc; @@ -443,16 +442,11 @@ term_word(struct termp *p, const char *w switch (esc) { case ESCAPE_UNICODE: uc = mchars_num2uc(seq + 1, sz - 1); - if (p->enc == TERMENC_ASCII) { - cp = ascii_uc2str(uc); - encode(p, cp, strlen(cp)); - } else - encode1(p, uc); break; case ESCAPE_NUMBERED: - c = mchars_num2char(seq, sz); - if ('\0' != c) - encode(p, &c, 1); + uc = mchars_num2char(seq, sz); + if (uc < 0) + continue; break; case ESCAPE_SPECIAL: if (p->enc == TERMENC_ASCII) { @@ -465,35 +459,50 @@ term_word(struct termp *p, const char *w if (uc > 0) encode1(p, uc); } - break; + continue; case ESCAPE_FONTBOLD: term_fontrepl(p, TERMFONT_BOLD); - break; + continue; case ESCAPE_FONTITALIC: term_fontrepl(p, TERMFONT_UNDER); - break; + continue; case ESCAPE_FONTBI: term_fontrepl(p, TERMFONT_BI); - break; + continue; case ESCAPE_FONT: /* FALLTHROUGH */ case ESCAPE_FONTROMAN: term_fontrepl(p, TERMFONT_NONE); - break; + continue; case ESCAPE_FONTPREV: term_fontlast(p); - break; + continue; case ESCAPE_NOSPACE: if (TERMP_SKIPCHAR & p->flags) p->flags &= ~TERMP_SKIPCHAR; else if ('\0' == *word) p->flags |= TERMP_NOSPACE; - break; + continue; case ESCAPE_SKIPCHAR: p->flags |= TERMP_SKIPCHAR; - break; + continue; default: - break; + continue; + } + + /* + * Common handling for Unicode and numbered + * character escape sequences. + */ + + if (p->enc == TERMENC_ASCII) { + cp = ascii_uc2str(uc); + encode(p, cp, strlen(cp)); + } else { + if ((uc < 0x20 && uc != 0x09) || + (uc > 0x7E && uc < 0xA0)) + uc = 0xFFFD; + encode1(p, uc); } } p->flags &= ~TERMP_NBRWORD; @@ -645,7 +654,7 @@ size_t term_strlen(const struct termp *p, const char *cp) { size_t sz, rsz, i; - int ssz, skip, c; + int ssz, skip, uc; const char *seq, *rhs; enum mandoc_esc esc; static const char rej[] = { '\\', ASCII_NBRSP, ASCII_HYPH, @@ -675,43 +684,60 @@ term_strlen(const struct termp *p, const switch (esc) { case ESCAPE_UNICODE: - c = mchars_num2uc(seq + 1, sz - 1); - if (p->enc == TERMENC_ASCII) { - rhs = ascii_uc2str(c); - rsz = strlen(rhs); - } else - sz += cond_width(p, c, &skip); + uc = mchars_num2uc(seq + 1, sz - 1); break; case ESCAPE_NUMBERED: - c = mchars_num2char(seq, ssz); - if ('\0' != c) - sz += cond_width(p, c, &skip); + uc = mchars_num2char(seq, ssz); + if (uc < 0) + continue; break; case ESCAPE_SPECIAL: - if (p->enc == TERMENC_ASCII) + if (p->enc == TERMENC_ASCII) { rhs = mchars_spec2str(p->symtab, seq, ssz, &rsz); - else { - c = mchars_spec2cp(p->symtab, + if (rhs != NULL) + break; + } else { + uc = mchars_spec2cp(p->symtab, seq, ssz); - if (c > 0) - sz += cond_width(p, c, &skip); + if (uc > 0) + sz += cond_width(p, uc, &skip); } - break; + continue; case ESCAPE_SKIPCHAR: skip = 1; - break; + continue; default: - break; + continue; } - if (NULL == rhs) - break; + /* + * Common handling for Unicode and numbered + * character escape sequences. + */ + + if (rhs == NULL) { + if (p->enc == TERMENC_ASCII) { + rhs = ascii_uc2str(uc); + rsz = strlen(rhs); + } else { + if ((uc < 0x20 && uc != 0x09) || + (uc > 0x7E && uc < 0xA0)) + uc = 0xFFFD; + sz += cond_width(p, uc, &skip); + continue; + } + } if (skip) { skip = 0; break; } + + /* + * Common handling for all escape sequences + * printing more than one character. + */ for (i = 0; i < rsz; i++) sz += (*p->width)(p, *rhs++); Index: chars.c =================================================================== RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/chars.c,v retrieving revision 1.64 retrieving revision 1.65 diff -Lchars.c -Lchars.c -u -p -r1.64 -r1.65 --- chars.c +++ chars.c @@ -107,15 +107,13 @@ mchars_spec2cp(const struct mchars *arg, return(ln != NULL ? ln->unicode : sz == 1 ? (unsigned char)*p : -1); } -char +int mchars_num2char(const char *p, size_t sz) { int i; - if ((i = mandoc_strntoi(p, sz, 10)) < 0) - return('\0'); - - return(i > 0 && i < 256 && isprint(i) ? i : '\0'); + i = mandoc_strntoi(p, sz, 10); + return(i >= 0 && i < 256 ? i : -1); } int Index: html.c =================================================================== RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/html.c,v retrieving revision 1.180 retrieving revision 1.181 diff -Lhtml.c -Lhtml.c -u -p -r1.180 -r1.181 --- html.c +++ html.c @@ -422,9 +422,13 @@ print_encode(struct html *h, const char break; case ESCAPE_NUMBERED: c = mchars_num2char(seq, len); + if (c < 0) + continue; break; case ESCAPE_SPECIAL: c = mchars_spec2cp(h->symtab, seq, len); + if (c <= 0) + continue; break; case ESCAPE_NOSPACE: if ('\0' == *p) @@ -433,9 +437,8 @@ print_encode(struct html *h, const char default: continue; } - if (c <= 0) - continue; - if (c < 0x20 || (c > 0x7E && c < 0xA0)) + if ((c < 0x20 && c != 0x09) || + (c > 0x7E && c < 0xA0)) c = 0xFFFD; if (c > 0x7E) printf("&#%d;", c); Index: mandoc.h =================================================================== RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/mandoc.h,v retrieving revision 1.167 retrieving revision 1.168 diff -Lmandoc.h -Lmandoc.h -u -p -r1.167 -r1.168 --- mandoc.h +++ mandoc.h @@ -425,7 +425,7 @@ __BEGIN_DECLS enum mandoc_esc mandoc_escape(const char **, const char **, int *); struct mchars *mchars_alloc(void); void mchars_free(struct mchars *); -char mchars_num2char(const char *, size_t); +int mchars_num2char(const char *, size_t); const char *mchars_uc2str(int); int mchars_num2uc(const char *, size_t); int mchars_spec2cp(const struct mchars *, -- To unsubscribe send an email to source+unsubscribe@mdocml.bsd.lv