From d672f8cb82878baf3834e938c4c416f4493952cf Mon Sep 17 00:00:00 2001 From: Ingo Schwarze Date: Sat, 15 Dec 2018 19:30:25 +0000 Subject: Several improvements to escape sequence handling. * Add the missing special character \_ (underscore). * Partial implementations of \a (leader character) and \E (uninterpreted escape character). * Parse and ignore \r (reverse line feed). * Add a WARNING message about undefined escape sequences. * Add an UNSUPP message about unsupported escape sequences. * Mark \! and \? (transparent throughput) and \O (suppress output) as unsupported. * Treat the various variants of zero-width spaces as one-byte escape sequences rather than as special characters, to avoid defining bogus forms with square brackets. * For special characters with one-byte names, do not define bogus forms with square brackets, except for \[-], which is valid. * In the form with square brackets, undefined special characters do not fall back to printing the name verbatim, not even for one-byte names. * Starting a special character name with a blank is an error. * Undefined escape sequences never abort formatting of the input string, not even in HTML output mode. * Document the newly handled escapes, and a few that were missing. * Regression tests for most of the above. --- mandoc.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'mandoc.h') diff --git a/mandoc.h b/mandoc.h index 6a2f1f30..0519d041 100644 --- a/mandoc.h +++ b/mandoc.h @@ -1,4 +1,4 @@ -/* $Id: mandoc.h,v 1.260 2018/12/14 05:18:02 schwarze Exp $ */ +/* $Id: mandoc.h,v 1.261 2018/12/15 19:30:26 schwarze Exp $ */ /* * Copyright (c) 2010, 2011, 2014 Kristaps Dzonsons * Copyright (c) 2012-2018 Ingo Schwarze @@ -169,6 +169,7 @@ enum mandocerr { MANDOCERR_FI_TAB, /* tab in filled text */ MANDOCERR_EOS, /* new sentence, new line */ MANDOCERR_ESC_BAD, /* invalid escape sequence: esc */ + MANDOCERR_ESC_UNDEF, /* undefined escape, printing literally: char */ MANDOCERR_STR_UNDEF, /* undefined string, using "": name */ /* related to tables */ @@ -231,6 +232,7 @@ enum mandocerr { MANDOCERR_TOOLARGE, /* input too large */ MANDOCERR_CHAR_UNSUPP, /* unsupported control character: number */ + MANDOCERR_ESC_UNSUPP, /* unsupported escape sequence: escape */ MANDOCERR_REQ_UNSUPP, /* unsupported roff request: request */ MANDOCERR_WHILE_NEST, /* nested .while loops */ MANDOCERR_WHILE_OUTOF, /* end of scope with open .while loop */ @@ -245,7 +247,9 @@ enum mandocerr { enum mandoc_esc { ESCAPE_ERROR = 0, /* bail! unparsable escape */ + ESCAPE_UNSUPP, /* unsupported escape; ignore it */ ESCAPE_IGNORE, /* escape to be ignored */ + ESCAPE_UNDEF, /* undefined escape; print literal character */ ESCAPE_SPECIAL, /* a regular special character */ ESCAPE_FONT, /* a generic font mode */ ESCAPE_FONTBOLD, /* bold font mode */ -- cgit v1.2.3-56-ge451