freetree234(macros);
}
+static void input_configure(input *in, paragraph *cfg) {
+ assert(cfg->type == para_Config);
+
+ if (!ustricmp(cfg->keyword, L"input-charset")) {
+ char *csname = utoa_dup(uadv(cfg->keyword), CS_ASCII);
+ in->charset = charset_from_localenc(csname);
+ sfree(csname);
+ }
+}
+
/*
* Can return EOF
*/
-static int get(input *in, filepos *pos) {
+static int get(input *in, filepos *pos, rdstringc *rsc) {
int pushbackpt = in->stack ? in->stack->npushback : 0;
if (in->npushback > pushbackpt) {
--in->npushback;
return c;
}
else if (in->currfp) {
- int c = getc(in->currfp);
- if (c == EOF) {
- fclose(in->currfp);
- in->currfp = NULL;
- }
- /* Track line numbers, for error reporting */
- if (pos)
- *pos = in->pos;
- if (in->reportcols) {
- switch (c) {
- case '\t':
- in->pos.col = 1 + (in->pos.col + TAB_STOP-1) % TAB_STOP;
- break;
- case '\n':
- in->pos.col = 1;
- in->pos.line++;
- break;
- default:
- in->pos.col++;
- break;
+ while (in->wcpos >= in->nwc) {
+
+ int c = getc(in->currfp);
+
+ if (c == EOF) {
+ fclose(in->currfp);
+ in->currfp = NULL;
+ return EOF;
+ }
+
+ if (rsc)
+ rdaddc(rsc, c);
+
+ /* Track line numbers, for error reporting */
+ if (pos)
+ *pos = in->pos;
+ if (in->reportcols) {
+ switch (c) {
+ case '\t':
+ in->pos.col = 1 + (in->pos.col + TAB_STOP-1) % TAB_STOP;
+ break;
+ case '\n':
+ in->pos.col = 1;
+ in->pos.line++;
+ break;
+ default:
+ in->pos.col++;
+ break;
+ }
+ } else {
+ in->pos.col = -1;
+ if (c == '\n')
+ in->pos.line++;
+ }
+
+ /*
+ * Do input character set translation, so that we return
+ * Unicode.
+ */
+ {
+ char buf[1];
+ char const *p;
+ int inlen;
+
+ buf[0] = (char)c;
+ p = buf;
+ inlen = 1;
+
+ in->nwc = charset_to_unicode(&p, &inlen,
+ in->wc, lenof(in->wc),
+ in->charset, &in->csstate,
+ NULL, 0);
+ assert(p == buf+1 && inlen == 0);
+
+ in->wcpos = 0;
}
- } else {
- in->pos.col = -1;
- if (c == '\n')
- in->pos.line++;
}
- /* FIXME: do input charmap translation. We should be returning
- * Unicode here. */
- return c;
+
+ return in->wc[in->wcpos++];
+
} else
return EOF;
}
int type;
int cmd, aux;
wchar_t *text;
+ char *origtext;
filepos pos;
};
enum {
token get_token(input *in) {
int c;
int nls;
+ int prevpos;
token ret;
rdstring rs = { 0, 0, NULL };
+ rdstringc rsc = { 0, 0, NULL };
filepos cpos;
ret.text = NULL; /* default */
- c = get(in, &cpos);
+ ret.origtext = NULL; /* default */
+ if (in->pushback_chars) {
+ rdaddsc(&rsc, in->pushback_chars);
+ sfree(in->pushback_chars);
+ in->pushback_chars = NULL;
+ }
+ c = get(in, &cpos, &rsc);
ret.pos = cpos;
if (iswhite(c)) { /* tok_white or tok_eop */
nls = 0;
+ prevpos = 0;
do {
if (isnl(c))
nls++;
- } while ((c = get(in, &cpos)) != EOF && iswhite(c));
+ prevpos = rsc.pos;
+ } while ((c = get(in, &cpos, &rsc)) != EOF && iswhite(c));
if (c == EOF) {
ret.type = tok_eof;
+ sfree(rsc.text);
return ret;
}
+ if (rsc.text) {
+ in->pushback_chars = dupstr(rsc.text + prevpos);
+ sfree(rsc.text);
+ }
unget(in, c, &cpos);
ret.type = (nls > 1 ? tok_eop : tok_white);
return ret;
} else if (c == EOF) { /* tok_eof */
ret.type = tok_eof;
+ sfree(rsc.text);
return ret;
} else if (c == '\\') { /* tok_cmd */
- c = get(in, &cpos);
+ rsc.pos = prevpos = 0;
+ c = get(in, &cpos, &rsc);
if (c == '-' || c == '\\' || c == '_' ||
c == '#' || c == '{' || c == '}' || c == '.') {
/* single-char command */
do {
rdadd(&rs, c);
len++;
- c = get(in, &cpos);
+ prevpos = rsc.pos;
+ c = get(in, &cpos, &rsc);
} while (ishex(c) && len < 5);
unget(in, c, &cpos);
} else if (iscmd(c)) {
do {
rdadd(&rs, c);
- c = get(in, &cpos);
+ prevpos = rsc.pos;
+ c = get(in, &cpos, &rsc);
} while (iscmd(c));
unget(in, c, &cpos);
}
*/
ret.type = tok_cmd;
ret.text = ustrdup(rs.text);
+ if (rsc.text) {
+ in->pushback_chars = dupstr(rsc.text + prevpos);
+ rsc.text[prevpos] = '\0';
+ ret.origtext = dupstr(rsc.text);
+ } else {
+ ret.origtext = dupstr("");
+ }
match_kw(&ret);
sfree(rs.text);
+ sfree(rsc.text);
return ret;
} else if (c == '{') { /* tok_lbrace */
ret.type = tok_lbrace;
+ sfree(rsc.text);
return ret;
} else if (c == '}') { /* tok_rbrace */
ret.type = tok_rbrace;
+ sfree(rsc.text);
return ret;
} else { /* tok_word */
/*
* a hyphen.
*/
ret.aux = FALSE; /* assumed for now */
+ prevpos = 0;
while (1) {
if (iswhite(c) || c=='{' || c=='}' || c=='\\' || c==EOF) {
/* Put back the character that caused termination */
} else {
rdadd(&rs, c);
if (c == '-') {
+ prevpos = rsc.pos;
ret.aux = TRUE;
break; /* hyphen terminates word */
}
}
- c = get(in, &cpos);
+ prevpos = rsc.pos;
+ c = get(in, &cpos, &rsc);
}
ret.type = tok_word;
ret.text = ustrdup(rs.text);
+ if (rsc.text) {
+ in->pushback_chars = dupstr(rsc.text + prevpos);
+ rsc.text[prevpos] = '\0';
+ ret.origtext = dupstr(rsc.text);
+ } else {
+ ret.origtext = dupstr("");
+ }
sfree(rs.text);
+ sfree(rsc.text);
return ret;
}
}
int c;
filepos cpos;
- c = get(in, &cpos);
+ c = get(in, &cpos, NULL);
unget(in, c, &cpos);
return (c == '{');
}
filepos cpos;
ret.type = tok_word;
- c = get(in, &cpos); /* expect (and discard) one space */
+ ret.origtext = NULL;
+ c = get(in, &cpos, NULL); /* expect (and discard) one space */
ret.pos = cpos;
if (c == ' ') {
- c = get(in, &cpos);
+ c = get(in, &cpos, NULL);
ret.pos = cpos;
}
while (!isnl(c) && c != EOF) {
int c2 = c;
- c = get(in, &cpos);
+ c = get(in, &cpos, NULL);
/* Discard \r just before \n. */
if (c2 != 13 || !isnl(c))
rdadd(&rs, c2);
* Destructor before token is reassigned; should catch most memory
* leaks
*/
-#define dtor(t) ( sfree(t.text) )
+#define dtor(t) ( sfree(t.text), sfree(t.origtext) )
/*
* Reads a single file (ie until get() returns EOF)
wchar_t uchr;
t.text = NULL;
+ t.origtext = NULL;
macros = newtree234(macrocmp);
already = FALSE;
int start_cmd = c__invalid;
par.words = NULL;
par.keyword = NULL;
+ par.origkeyword = NULL;
whptr = &par.words;
/*
if (needkw > 0) {
rdstring rs = { 0, 0, NULL };
+ rdstringc rsc = { 0, 0, NULL };
int nkeys = 0;
filepos fp;
(t.type == tok_cmd && t.cmd == c__nbsp) ||
(t.type == tok_cmd && t.cmd == c__escaped)) {
if (t.type == tok_white ||
- (t.type == tok_cmd && t.cmd == c__nbsp))
+ (t.type == tok_cmd && t.cmd == c__nbsp)) {
rdadd(&rs, ' ');
- else
+ rdaddc(&rsc, ' ');
+ } else {
rdadds(&rs, t.text);
+ rdaddsc(&rsc, t.origtext);
+ }
}
if (t.type != tok_rbrace) {
error(err_kwunclosed, &t.pos);
continue;
}
rdadd(&rs, 0); /* add string terminator */
+ rdaddc(&rsc, 0); /* add string terminator */
dtor(t), t = get_token(in); /* eat right brace */
}
- rdadd(&rs, 0); /* add string terminator */
+ rdadd(&rs, 0); /* add string terminator */
+ rdaddc(&rsc, 0); /* add string terminator */
/* See whether we have the right number of keywords. */
if ((needkw & 48) && nkeys > 0)
}
par.keyword = rdtrim(&rs);
+ par.origkeyword = rdtrimc(&rsc);
/* Move to EOP in case of needkw==8 or 16 (no body) */
if (needkw & 24) {
already = TRUE;/* inhibit get_token at top of loop */
prev_para_type = par.type;
addpara(par, ret);
+
+ if (par.type == para_Config) {
+ input_configure(in, &par);
+ }
continue; /* next paragraph */
}
}
* delimiting the text marked by the link.
*/
dtor(t), t = get_token(in);
- /*
- * Special cases: \W{}\c, \W{}\e, \W{}\cw
- */
sitem = mknew(struct stack_item);
sitem->fpos = wd.fpos;
sitem->type = stack_hyper;
+ /*
+ * Special cases: \W{}\i, \W{}\ii
+ */
+ if (t.type == tok_cmd &&
+ (t.cmd == c_i || t.cmd == c_ii)) {
+ if (indexing) {
+ error(err_nestedindex, &t.pos);
+ } else {
+ /* Add an index-reference word with no
+ * text as yet */
+ wd.type = word_IndexRef;
+ wd.text = NULL;
+ wd.alt = NULL;
+ wd.aux = 0;
+ wd.breaks = FALSE;
+ indexword = addword(wd, &whptr);
+ /* Set up a rdstring to read the
+ * index text */
+ indexstr = nullrs;
+ /* Flags so that we do the Right
+ * Things with text */
+ index_visible = (type != c_I);
+ index_downcase = (type == c_ii);
+ indexing = TRUE;
+ idxwordlist = NULL;
+ idximplicit = &idxwordlist;
+
+ sitem->type |= stack_idx;
+ }
+ dtor(t), t = get_token(in);
+ }
+ /*
+ * Special cases: \W{}\c, \W{}\e, \W{}\cw
+ */
if (t.type == tok_cmd &&
(t.cmd == c_e || t.cmd == c_c || t.cmd == c_cw)) {
if (style != word_Normal)
in->currfp = fopen(in->filenames[in->currindex], "r");
if (in->currfp) {
setpos(in, in->filenames[in->currindex]);
+ in->charset = in->defcharset;
+ in->csstate = charset_init_state;
+ in->wcpos = in->nwc = 0;
+ in->pushback_chars = NULL;
read_file(&hptr, in, idx);
}
in->currindex++;