summary refs log tree commit diff stats
path: root/tests/generics/tgenericlambda.nim
Commit message (Expand)AuthorAgeFilesLines
* use 'using' instead of 'sig' keyword; cleans up new features a bitAndreas Rumpf2016-02-291-3/+3
* fix #715 againZahary Karadjov2014-03-161-1/+6
* fix some trivial errors in the test suite and some more regressions caused by...Zahary Karadjov2014-02-181-1/+9
* quite messy implementation of generic lambdas, needs reworking; fixes #715Zahary Karadjov2014-02-171-0/+10
'>84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262





































































































































































































































































                                                                              
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <hyphen.h>
#include "config.h"

/* Read a tag into a character array and return its length. */
int
readtag(char *tag, FILE *in, FILE *out)
{
	char ch;
	int i = 0;

	/* Data after a space in a tag is irrelevant. */
	while ((ch = fgetc(in)) != '>' && ch != ' ') {
		fputc(ch, out);
		tag[i] = ch;
		++i;
	}

	if (ch == ' ') {
		/* Seek to the end of the tag. */
		while (ch != '>'
		&& ch != EOF) {
			fputc(ch, out);
			ch = fgetc(in);
		}
		if (ch == EOF) {
			return -1;
		}
		fputc(ch, out);
	}
	else
		fputc(ch, out);

	tag[i] = '\0';
	return i;
}

int
cmptag(char *tag2, FILE *in, FILE *out)
{
	char tag1[MAXWLEN];
	readtag(tag1, in, out);

	return strcmp(tag1, tag2);
}

int
checktag(char *tag, int tagamt, FILE *in, FILE *out)
{
	int i;
	for (i = 0; i < tagamt; ++i)
		if (strcmp(tag, taglist[i]) == 0)
			return i;
	return -1;
}

/* Check if a character should be skipped. */
int
checkskip(char ch, int skiplen)
{
	int i;
	for (i = 0; i < skiplen; ++i)
		if (ch == skip[i])
			return 1;

	return 0;
}

const char *punct = "';.,\"!?:";
/* Check if a character is punctuation. */
int
checkpunct(char ch)
{
	int i;
	for (i = 0; punct[i] != '\0'; ++i)
		if (ch == punct[i])
			return 1;

	return 0;
}

const char *blank = " \n\r\t";
/* Check if a character is a blank. */
int
checkblank(char ch)
{
	int i;
	for (i = 0; blank[i] != '\0'; ++i)
		if (ch == blank[i])
			return 1;

	return 0;
}

/* Loop until the body is found. */
int
findbody(FILE *in, FILE *out)
{
	char ch;
	while ((ch = fgetc(in)) != EOF) {
		fputc(ch, out);
		if (ch == '<'
		&& cmptag("body", in, out) == 0)
			return 1;
	}

	return 0;
}

/* Hyphenate a word, by means of hyphen library.
This is done so as to leverage sufficient hyphenation
patterns, with the ones used here having been taken
from those developed for TeX. */
void
hypword(char *word, int len, FILE *in, FILE *out, HyphenDict *dict)
{
	if (len < MINWLEN) {
		fprintf(out, "%s", word);
		return;
	}

	char *hyphens = calloc(len + 6, sizeof(char));
	char *hyphword = calloc(len << 1, sizeof(char));
	char **rep = NULL;
	int *pos = NULL, *cut = NULL;
	hnj_hyphen_hyphenate2(dict, word, len, hyphens,
		hyphword, &rep, &pos, &cut);

/*	fprintf(stderr, "%s\n%s\n%s\n", word, hyphens, hyphword); */

	/* Process the given hyphenation. */
	int i;
	char oldch = ' ', oldoldch = '\0';
	for (i = 0; i < strlen(hyphword); ++i) {
		if (hyphword[i] == '=' && oldch != ' '
			&& oldoldch != ' ')
			fputs("&shy;", out);
		else if (hyphword[i] != '=')
			fputc(hyphword[i], out);

		oldoldch = oldch;
		oldch = hyphword[i];
	}

	free(hyphens);
	free(hyphword);
}

/* Hyphenate the words within a tag. */
void
hyptag(FILE *in, FILE *out, int skiplen, char *tag, HyphenDict *dict)
{
	char ch, word[MAXWLEN], term[MAXWLEN] = "/";
	int i = 0;

	strcat(term, tag);

	while ((ch = fgetc(in)) != EOF) {
		if (i < 0) {
			fputc(ch, out);
			++i;
			if (checkskip(ch, skiplen)) i -= 3;
			continue;
		}
		if (checkblank(ch)) {
			word[i] = '\0';
			hypword(word, i, in, out, dict);
			i = 0;
		}
		if (checkpunct(ch)) {
			word[i] = '\0';
			hypword(word, i, in, out, dict);
			fputc(ch, out);
			i = 0;
		}
		else if (checkskip(ch, skiplen)) {
			word[i] = '\0';
			fputs(word, out);
			fputc(ch, out);
			/* A simple way of working around
			HTML character codes. Each is 5 ( epsiv )
			 or 6 ( hellip ) characters long, plus '&' and ';'. */
			i = -3;
		}		
		/* Check for closing tag. */
		else if (ch == '<') {
			word[i] = ch;
			++i;
			word[i] = '\0';
			hypword(word, i, in, out, dict);
			i = 0;
			readtag(word, in, out);
			if (strcmp(word, term) == 0) break;
		}
		else {
			word[i] = ch;
			++i;
		}
		if (i == MAXWLEN - 1) {
			word[i] = '\0';
			hypword(word, i, in, out, dict);
			i = 0;
		}
	}
}

/* Hyphenate HTML input via `&shy;'.
hyp [in] [out] */
int
main(int argc, char **argv)
{
	FILE *in;
	if (argc < 2)
		in = stdin;
	else {
		in = fopen(argv[1], "r");
		if (in == NULL) {
			printf("%s %s\n", argv[1], "inaccessible.");
			return 1;
		}
	}

	FILE *out;
	if (argc < 3)
		out = stdout;
	else {
		out = fopen(argv[2], "w");
		if (out == NULL) {
			printf("%s %s\n", argv[2], "inaccessible.");
			return 2;
		}
	}

	if (findbody(in, out) == 0) {
		puts("There is no body.");
		return 3;
	}

	HyphenDict *dict = hnj_hyphen_load(dictfile);
	if (dict == NULL) {
		puts("Dict not readable.");
		return 4;
	}
	dict->utf8 = 1;

	int tagamt = 0;
	while (taglist[tagamt][0] != '\0')
		++tagamt;
	int skiplen = strlen(skip);

	char ch, tag[MAXWLEN];
	int len;
	while ((ch = fgetc(in)) != EOF) {
		fputc(ch, out);
		if (ch == '<' && (len = readtag(tag, in, out)) > 0
			&& checktag(tag, tagamt, in, out) != -1)
			hyptag(in, out, skiplen, tag, dict);
	}
	return 0;
}