summaryrefslogtreecommitdiff
path: root/support/word2x/html-fmt.cc
diff options
context:
space:
mode:
authorNorbert Preining <norbert@preining.info>2019-09-02 13:46:59 +0900
committerNorbert Preining <norbert@preining.info>2019-09-02 13:46:59 +0900
commite0c6872cf40896c7be36b11dcc744620f10adf1d (patch)
tree60335e10d2f4354b0674ec22d7b53f0f8abee672 /support/word2x/html-fmt.cc
Initial commit
Diffstat (limited to 'support/word2x/html-fmt.cc')
-rw-r--r--support/word2x/html-fmt.cc487
1 files changed, 487 insertions, 0 deletions
diff --git a/support/word2x/html-fmt.cc b/support/word2x/html-fmt.cc
new file mode 100644
index 0000000000..11344d6530
--- /dev/null
+++ b/support/word2x/html-fmt.cc
@@ -0,0 +1,487 @@
+/* $Id: html-fmt.cc,v 1.1 1997/04/23 00:45:06 dps Exp dps $ */
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif /* HAVE_CONFIG_H */
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#ifdef HAVE_UNISTD_H
+#include <unistd.h>
+#endif /* HAVE_UNISTD_H */
+#ifdef HAVE_CTYPE_H
+#include <ctype.h>
+#endif /* HAVE_CTYPE_H */
+#ifdef HAVE_SYS_STAT_H
+#include <sys/stat.h>
+#endif /* HAVE_SYS_STAT_H */
+#include "interface.h"
+#include "lib.h"
+#include "html-table.h"
+#include "fmt-html.h"
+
+static const cmap html_map[]=
+{
+ { '\n', "<BR>\n" }, // Newline
+ { 0x1E, "-" }, // Unbreakable join
+ { 0x1F, "\\-" }, // Soft hypen
+ { '<', "&lt;" }, // #
+ { '>', "&gt;" }, // $
+ { '&', "&amp;" }, // &
+ { 0x85, "..." }, // Dots
+ { 0x91, "`" }, // 91 = left quote (15th element)
+ { 0x92, "'" }, // 92 = right quote
+ { 0x93, "``" }, // 93 = opening double quote
+ { 0x94, "''" }, // 94 = closing double quote
+ { 0x96, "--" }, // em-dash
+ { 0x97, "---" }, // en-dash (20th element)
+ { 0x99, "(TM)" }, // Trademark
+ { 0xA0, " " }, // Unbreakable space
+ { 0xA3, "&lt;=" }, // <= came out as A3, also pounds
+ { 0xA9, "(C)" }, // Copyright
+ { 0xAB, "&lt;&lt;" }, // Openning << quotes (25th element)
+ { 0xAE, "(R)" }, // reserved sign
+ { 0xB3, "&gt;=" }, // Greater than or = came out as B3
+ { 0xBB, "&gt;&gt;" }, // Closing >> quotes (28th element)
+ { 0xDF, "&szlig;" }, // beta
+ { 0xE4, "&auml;" }, // a with umlualt
+ { 0xE9, "&egrave;" }, // e grave??
+ { 0xF1, "&ntidle" }, // n bar
+ { 0xF6, "&ouml;" }, // o with umlualt
+ { 0xFA, "\\.u" }, // u with dot?
+ { 0xFC, "&uuml;" }, // u with umlualt.
+};
+
+tblock *__html_do_map(const char *s)
+{
+ tblock *out;
+
+ out = map_string(s, html_map);
+ return out;
+}
+
+/* Preamble */
+static void h_preamble(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ time_t now;
+ struct stat st;
+ char *tnow, *tdoc;
+
+ t=t;
+ d=d;
+
+ now=time(NULL);
+ tnow=(fmt->date)(now);
+
+ if (fstat(fileno(out), &st)==-1)
+ st.st_mtime=now;
+ tdoc=fmt->date(st.st_mtime);
+
+ fprintf(out,
+ "<!-- Generated by word2x on %s-->\n"
+ "\n"
+ "<HTML>\n"
+ "<HEAD>\n"
+ " <TITLE>Word document from %s</TITLE>"
+ "</HEAD>\n"
+ "<BODY>\n",
+ tnow, tdoc);
+ free(tnow);
+ free(tdoc);
+}
+
+/* Postamble */
+static void h_postamble(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *dp;
+ fmt=fmt;
+ t=t;
+ dp=(struct html_data *) d;
+
+ fputs("</BODY></HTML>\n", out);
+}
+
+/* Allocate local data */
+static void *allocate_html(void)
+{
+ struct html_data *tdata;
+ int i;
+
+ tdata = new(struct html_data);
+ tdata->tabl = NULL;
+ tdata->last_tc = NULL;
+ tdata->unit_d.unit_type = 1;
+ tdata->list_flg = 0;
+ for (i=0; i<4; i++)
+ tdata->unit_d.unit_number[i]=-1;
+
+ return tdata;
+}
+
+/* Free local data */
+static void free_html(void *d)
+{
+ struct html_data *tdata;
+
+ tdata=(struct html_data *) d;
+ if (tdata->tabl!=NULL)
+ delete(tdata->tabl);
+}
+
+
+static void html_code(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ d=d;
+ switch(*(t->data.d))
+ {
+ case CH_PAGE:
+ if (fmt->flags.new_pages)
+ fputs("\n<HR>\n", out);
+ break;
+
+ default:
+ break;
+ }
+}
+
+
+struct list_info
+{
+ const char *ltype; // List type from reader
+ const char *start; // Start tag
+ const char *end; // End tag
+};
+
+static const struct list_info *ltype_info(const char *type)
+{
+ static const struct list_info list_inf[]=
+ {
+ { "listAlpha", "<OL TYPE=\"A\">", "</OL>" }, // Netscape extension
+ { "listalpha", "<OL TYPE=\"a\">", "</OL>" }, // Netscape extension
+ { "enumerate", "<OL>", "</OL>" }, // Standard
+ { "itemize", "<UL>", "</UL>" }, // Standard
+ };
+
+ unsigned i;
+
+ for (i=0; i<N(list_inf); i++)
+ {
+ if (strcmp(type, list_inf[i].ltype)==0)
+ return (list_inf+i);
+ }
+ return NULL;
+}
+
+/* item */
+static void html_item(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *dp;
+ fmt=fmt;
+ t=t;
+ out=out;
+ dp=(struct html_data *) d;
+
+ dp->list_flg=1;
+}
+
+
+/* start list, have to convert from *TeX types... */
+static void html_list(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ const struct list_info *linf;
+ const char *s;
+
+ fmt=fmt;
+ d=d;
+ linf=ltype_info(t->data.d);
+ if (linf==NULL)
+ {
+ cerr<<"Unknown list type "<<t->data.d<<" treated as bulleted list\n";
+ s="<UL>";
+ }
+ else
+ {
+ s=linf->start;
+ }
+ fprintf(out, "\n%s\n", s);
+}
+
+/* end list, have to convert from *TeX types... */
+static void html_end_list(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ const struct list_info *linf;
+ const char *s;
+
+ fmt=fmt;
+ d=d;
+ fmt=fmt;
+ d=d;
+ linf=ltype_info(t->data.d);
+ if (linf==NULL)
+ {
+ cerr<<"Unknown list type "<<t->data.d<<" treated as bulleted list\n";
+ s="</UL>";
+ }
+ else
+ s=linf->end;
+ fprintf(out, "\n%s\n", s);
+}
+
+/*
+ * Paragraphs are easy, but get complicated due to need to work out
+ * which things are actually chapter headings, etc
+ */
+static void fold_para(const tok_seq::tok *tok, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ tblock *b, *ts, op;
+ const char *s, *t, *pt, *unit_html="P";
+ struct html_data *dp;
+ int has_num, i, j;
+ struct unit_number u_num;
+
+ static const char *const sects[]=
+ {
+ "H1", "H2", "H3", "H4"
+ };
+ static const char *const sects_english[]=
+ {
+ "chapter", "section", "subsection", "subsubsection"
+ };
+
+ dp = (struct html_data *) d;
+
+ /* Even this much is under 100%!! */
+ pt=(tok->data.d);
+
+ if (*pt=='\0' && dp->list_flg==1)
+ return;
+
+ if (dp->last_tc != NULL)
+ {
+ if (strcmp(dp->last_tc, pt)==0)
+ {
+ unit_html=sects[dp->unit_d.unit_type];
+ }
+
+ else
+ {
+ s=dp->last_tc+strlen(dp->last_tc)-strlen(pt);
+ if (strcmp(s, pt)==0)
+ {
+ /* Find type */
+ for (i=0; i<(int) N(sects_english); i++)
+ {
+ if (strncasecmp(dp->last_tc, sects_english[i],
+ strlen(sects_english[i]))==0)
+ break;
+ }
+ t = dp->last_tc+strlen(sects_english[i]);
+ has_num = get_part_num(t,s);
+ unit_html=sects[i]; // Set the section type
+
+ /* Update the control data */
+ if (dp->unit_d.unit_number[i]==-1)
+ {
+ dp->unit_d.unit_number[i]=(has_num==-1) ? 1 : has_num;
+ for (j=i+1; j<(int) N(sects); j++)
+ dp->unit_d.unit_number[j]=0;
+ }
+ if (i<(int) N(sects)-1)
+ dp->unit_d.unit_type=i+1;
+ else
+ dp->unit_d.unit_type=i;
+ }
+ }
+ free((void *) dp->last_tc);
+ dp->last_tc=NULL;
+ }
+ else
+ {
+ if (dp->list_flg)
+ {
+ op.add("<Li>");
+ }
+ else
+ {
+ if (strlen(pt)>0 && strlen(pt)<PAR_TRESHOLD_LEN)
+ {
+ if (strcasecmp(pt,"Appendix")==0)
+ {
+ dp->unit_d.unit_type=
+ (dp->unit_d.unit_number[0]==-1) ? 1 : 0;
+
+ /* Output the heading level */
+ unit_html=sects[dp->unit_d.unit_type];
+ for (j=dp->unit_d.unit_type+1; j<(int) N(sects); j++)
+ dp->unit_d.unit_number[j]=0;
+ }
+ else if (strcasecmp(pt,"Bibliography")==0)
+ {
+ dp->unit_d.unit_type=
+ (dp->unit_d.unit_number[0]==-1) ? 1 : 0;
+ for (j=dp->unit_d.unit_type+1; j<(int) N(sects); j++)
+ dp->unit_d.unit_number[j]=0;
+ }
+ else
+ {
+ u_num=n_unit_probe(pt, &(dp->unit_d));
+
+ if (u_num.unit_num!=-1)
+ {
+ i=u_num.offset;
+ unit_html=sects[u_num.unit_num];
+ }
+ }
+ }
+ }
+ dp->list_flg=0;
+ }
+ /* Record the unit type started */
+ dp->unit_html=unit_html;
+ /* Insert the start tag and eneter paragraoh if not in one */
+ if (!dp->par_flg)
+ {
+ dp->par_flg = 1;
+ op.add("<");
+ op.add(unit_html);
+ op.add('>');
+ }
+ /* Add the text */
+ ts = map_string(pt, html_map);
+ op.add(*ts);
+ delete(ts);
+ /* fold the line */
+ b = word_wrap(op, "\n", "\n", fmt->maxline, 0);
+ fputs((*b), out);
+ delete(b);
+}
+
+/* End of paragraph, outputs the end tag */
+static void end_para(const tok_seq::tok *tok, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *dp;
+
+ tok=tok;
+ fmt=fmt;
+ dp=(struct html_data *) d;
+ dp->par_flg=0;
+
+ fputs("</",out);
+ fputs(dp->unit_html, out);
+ fputs(">\n\n", out);
+}
+
+/* Start a table === allocate table and initialise */
+static void alloc_tbl(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ out=out;
+ fmt=fmt;
+ tdata=(struct html_data *) d;
+ tdata->col=0;
+ tdata->row=0;
+ tdata->tabl=new(html_table)(t->data.table.cols, t->data.table.rows);
+ tdata->par_flg=0;
+}
+
+
+/* End of a table==print the table */
+static void format_tbl(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ t=t;
+ tdata=(struct html_data *) d;
+ tdata->tabl->print_table(fmt->maxline, out); // Print table
+ delete(tdata->tabl);
+ tdata->tabl=NULL;
+}
+
+/* start row==set column to 0 */
+static void start_row(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ out=out;
+ fmt=fmt;
+ t=t;
+ tdata=(struct html_data *) d;
+ tdata->col=0;
+}
+
+/* end row==add one to row */
+static void inc_row(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ fmt=fmt;
+ t=t;
+ out=out;
+ tdata=(struct html_data *) d;
+ tdata->row++;
+}
+
+
+/* Start field === set field */
+static void set_field(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ tdata=(struct html_data *) d;
+ out=out;
+ fmt=fmt;
+ tdata->tabl->set(tdata->col, tdata->row, t->data.d);
+}
+
+/* end field==add one to col */
+static void inc_col(const tok_seq::tok *t, const docfmt *fmt, FILE *out,
+ void *d)
+{
+ struct html_data *tdata;
+
+ out=out;
+ fmt=fmt;
+ t=t;
+ tdata=(struct html_data *) d;
+ tdata->col++;
+}
+
+
+
+/* pointers to the functions that do the work */
+docfmt htmlfmt=
+{
+ { 1 }, // Keep page breaks
+ 76, // Width
+ "\n", // Use \n as line ends
+ allocate_html, // Allocate space
+ free_html, // Free text
+ {
+ { h_preamble, h_postamble }, // End and start of document
+ { fold_para, end_para }, // Paragraph
+ { alloc_tbl, format_tbl }, // Start/end table
+ { set_field, inc_col }, // Start/end field
+ { start_row, inc_row }, // Start/end row
+ { html_embed, null_proc }, // Throw away embed messages
+ { html_list, html_end_list }, // Start/end list
+ { html_item, null_proc }, // Start/end item
+ { html_code, null_proc }, // Code ends do not occur
+ { null_proc, null_proc } // Do not understanding anything else
+ }
+} ;
+
+
+