1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512
|
/*
* Copyright (C) 2002-2004 Pekka Enberg <penberg@iki.fi>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "buffer.h"
#include "indent.h"
/*
* Functions the generated scanner uses.
*/
static void xml_declaration(void);
static void cdata_section(void);
static void doctype_declaration(void);
static void start_tag(void);
static void end_tag(void);
static void empty_element_tag(void);
static void comment(void);
static void content(void);
static void processing_insn(void);
static void do_newline(struct buffer * buffer, const char * text);
#include "lex.yy.c"
/*
* Flex unput() wrapper
*/
extern void do_unput(int);
/*
* Functions we use.
*/
static void newline(void);
/*
* We have three buffers: primary, secondary, and tag buffer. The first one
* has all data before previous start-tag, second one has data encountered
* after previous start-tag, and the last one _has_ the start-tag.
*/
struct buffer primary_buf;
struct buffer secondary_buf;
struct buffer tag_buf;
struct buffer * current_buf;
/*
* Indent options. To be modified only trough set_options.
*/
static char indent_char;
static int num_indent_chars;
static bool force_newline_after_start_tag;
static bool force_newline_after_end_tag;
static bool force_newline_before_start_tag;
static bool force_newline_before_end_tag;
static bool force_always;
static int max_columns;
static bool wrap_long_lines;
static FILE * indent_output;
/*
* Default options.
*/
#define DEFAULT_INDENT_CHAR ' '
#define DEFAULT_NUM_INDENT_CHARS 4
/* Set default indent options. */
void indent_options_set_defaults(struct indent_options * opts)
{
opts->indent_char = DEFAULT_INDENT_CHAR;
opts->num_indent_chars = DEFAULT_NUM_INDENT_CHARS;
opts->max_columns = -1;
opts->wrap_long_lines = false;
opts->force_newline_after_start_tag = true;
opts->force_newline_after_end_tag = true;
opts->force_newline_before_start_tag = true;
opts->force_newline_before_end_tag = true;
opts->force_always = false;
}
/* Set indent options. */
static void set_options(struct indent_options * opts)
{
indent_char = opts->indent_char;
num_indent_chars = opts->num_indent_chars;
max_columns = opts->max_columns;
wrap_long_lines = opts->wrap_long_lines;
force_newline_after_start_tag = opts->force_newline_after_start_tag;
force_newline_after_end_tag = opts->force_newline_after_end_tag;
force_newline_before_start_tag = opts->force_newline_before_start_tag;
force_newline_before_end_tag = opts->force_newline_before_end_tag;
force_always = opts->force_always;
}
#define BUFFER_INITIAL_CAPACITY 1024
void indent(FILE * input, FILE * output, struct indent_options * opts)
{
set_options(opts);
buffer_init(&primary_buf, BUFFER_INITIAL_CAPACITY);
buffer_init(&secondary_buf, BUFFER_INITIAL_CAPACITY);
buffer_init(&tag_buf, BUFFER_INITIAL_CAPACITY);
current_buf = &primary_buf;
yyin = input;
indent_output = output;
yylex();
/*
* There might not have been a newline before EOF.
*/
buffer_flush(current_buf, indent_output);
buffer_release(&primary_buf);
buffer_release(&secondary_buf);
buffer_release(&tag_buf);
}
/* Print indent characters. */
static void print_indent(FILE * output, int indent_level)
{
int i;
for (i = 0; i < (num_indent_chars * indent_level); i++) {
fputc(indent_char, output);
}
}
static void xml_declaration(void)
{
buffer_push_str(current_buf, yytext);
}
static void cdata_section(void)
{
buffer_push_str(current_buf, yytext);
}
static void doctype_declaration(void)
{
buffer_push_str(current_buf, yytext);
}
/* XML end of line characters. */
#define CARRIAGE_RETURN 0x0D
#define LINE_FEED 0x0A
#define NEL 0x85
static inline bool is_newline(int current)
{
if ((CARRIAGE_RETURN == current)
|| (LINE_FEED == current)
|| (NEL == current))
return true;
return false;
}
/* Check for whitespace character. */
static inline bool is_whitespace(int c)
{
return ((c == ' ') || (c == '\f') || (c == '\t') || (c == '\v'));
}
/* Eat whitespace from stream. */
static void eat_whitespace(void)
{
for (;;) {
int current = input();
if (!is_whitespace(current)) {
do_unput(current);
break;
}
}
}
static int indent_level = 0;
static int indent_delta = 0;
/* Force newline before tag. Use buffer for getting current character. */
static void force_newline_before_tag(struct buffer * buffer)
{
int current;
if (buffer_size(buffer) == 0) {
/*
* We just did a newline, no need to force it.
*/
return;
}
current = buffer_pop_char(buffer);
buffer_push_char(buffer, current);
if (!is_newline(current)) {
do_newline(buffer, "\n");
if (is_whitespace(current)) {
eat_whitespace();
return;
}
}
}
/* Force newline after tag. Use lexer to get current character. */
static void force_newline_after_tag(struct buffer * buffer)
{
int current = input();
do_unput(current);
if (!is_newline(current)) {
do_newline(buffer, "\n");
eat_whitespace();
}
}
static bool using_primary_buf(void)
{
return current_buf == &primary_buf;
}
/* Merge tag and secondary buffer to primary buffer. Force newlines if
necessary. This routine is used with start-tags. */
static void merge_buffers_start_tag(void)
{
if (force_newline_before_start_tag) {
force_newline_before_tag(&primary_buf);
}
buffer_copy(&primary_buf, &tag_buf);
indent_delta++;
if (force_newline_after_start_tag) {
force_newline_after_tag(&primary_buf);
}
buffer_copy(&primary_buf, &secondary_buf);
buffer_clear(&tag_buf);
buffer_clear(&secondary_buf);
current_buf = &primary_buf;
}
/* Merge tag and secondary buffer back to primary buffer. */
static void merge_buffers(void)
{
buffer_copy(&primary_buf, &tag_buf);
buffer_copy(&primary_buf, &secondary_buf);
buffer_clear(&tag_buf);
buffer_clear(&secondary_buf);
current_buf = &primary_buf;
/* We just processed a start-tag so bump up indent_delta. */
indent_delta++;
}
/* Force newline for wrapping line. Use lexer to get current character and
do not eat whitespace from next line. */
static void force_newline_for_wrap(struct buffer * buffer)
{
int current = input();
/*
* Flush all pending stuff before doing the newline.
*/
if (!using_primary_buf()) {
merge_buffers();
}
do_newline(current_buf, "\n");
if (!is_newline(current))
do_unput(current);
}
static void start_tag(void)
{
char * tmp;
/*
* Save text because merge_buffers_start_tag may trash it.
*/
tmp = strdup(yytext);
if (!using_primary_buf()) {
/*
* This is second start-tag. Thus first one has children. We can force
* newline here if we want.
*/
merge_buffers_start_tag();
}
buffer_push_str(&tag_buf, tmp);
current_buf = &secondary_buf;
free(tmp);
}
static void end_tag(void)
{
bool can_force_newline;
char * tmp;
/*
* Save text because force_newline_before_tag can trash it.
*/
tmp = strdup(yytext);
if (using_primary_buf()) {
can_force_newline = true;
} else {
/* The element didn't have any children - force newline only if user
explicity requested that. */
merge_buffers();
can_force_newline = force_always;
}
if (force_newline_before_end_tag && can_force_newline) {
force_newline_before_tag(current_buf);
}
buffer_push_str(current_buf, tmp);
indent_delta--;
if (force_newline_after_end_tag && can_force_newline) {
force_newline_after_tag(current_buf);
}
free(tmp);
}
static void empty_element_tag(void)
{
bool can_force_newline;
char * tmp;
/*
* Save text because force_newline_before_tag can trash it.
*/
tmp = strdup(yytext);
/* We treat empty element tag as a "merged" start-tag and end-tag.
Therefore we use start-tag options before the tag and end-tag
options after the tag. */
if (!using_primary_buf()) {
/*
* This is second start-tag. Thus first one has children. We can force
* newline here if we want.
*/
merge_buffers_start_tag();
can_force_newline = force_always;
} else {
can_force_newline = true;
}
buffer_push_str(current_buf, tmp);
if (force_newline_after_end_tag && can_force_newline) {
/* Empty element never has any children. Force newline only if user
explicitly requested it. */
force_newline_after_tag(current_buf);
}
free(tmp);
}
static int input_and_push(void)
{
int ret = input();
if (ret != EOF) buffer_push_char(current_buf, ret);
return ret;
}
static void comment(void)
{
int c;
buffer_push_str(current_buf, yytext);
for (;;) {
while ((c = input_and_push()) != '-' &&
c != EOF)
;
if ((c = input_and_push()) != '-') {
continue;
}
if ((c = input_and_push()) == '>') {
break;
}
}
}
static void do_newline(struct buffer * buffer, const char * text)
{
buffer_push_str(buffer, text);
if (indent_delta < 0) indent_level += indent_delta;
print_indent(indent_output, indent_level);
if (indent_delta > 0) indent_level += indent_delta;
indent_delta = 0;
buffer_flush(buffer, indent_output);
}
static void newline(void)
{
/*
* Flush all pending stuff before doing the newline.
*/
if (!using_primary_buf()) {
merge_buffers();
}
do_newline(current_buf, "\n");
eat_whitespace();
}
/*
* We assume tab is equal to 8 spaces.
*/
#define TAB_SIZE 8
static unsigned long indent_size(void)
{
return (indent_char == '\t'
? indent_level * TAB_SIZE
: indent_level * num_indent_chars);
}
static bool need_wrap(struct buffer * buffer)
{
if (buffer == &primary_buf)
return buffer_size(buffer) + indent_size() == max_columns;
else
return (buffer_size(&primary_buf) + buffer_size(&tag_buf)
+ buffer_size(buffer) + indent_size()) >= max_columns;
}
/*
* We detect EOF by getting a call to yywrap() when the only input file
* is completely read.
*/
static bool is_at_eof;
int yywrap() {
is_at_eof = 1;
return 1; /* 1=nothing more to read */
}
static void content(void)
{
char current;
/*
* We should get one character at a time.
*/
assert(yyleng == 1); /* strlen(yytext) fails at NUL or EOF */
current = yytext[0];
if (is_at_eof)
return;
if (is_newline(current)) {
newline();
return;
}
buffer_push_char(current_buf, current);
/*
* Forcing newline changes 'text' so lets do it after we've pushed
* it to the buffer.
*/
if (wrap_long_lines && need_wrap(current_buf)) {
struct buffer tmp;
buffer_init(&tmp, buffer_size(current_buf));
/*
* Find last character that was not whitespace
*/
for (;;) {
int c;
if (buffer_size(current_buf) == 0)
break;
c = buffer_pop_char(current_buf);
if (is_whitespace(c)) {
/*
* Do not push whitespace because it would appear
* after the newline.
*/
break;
}
/*
* Characters are put in tmp buffer in reverse order.
*/
buffer_push_char(&tmp, c);
}
force_newline_for_wrap(current_buf);
/*
* Restore non-wrapped text into buffer.
*/
while (buffer_size(&tmp) > 0) {
buffer_push_char(current_buf, buffer_pop_char(&tmp));
}
buffer_release(&tmp);
}
}
static void processing_insn(void)
{
buffer_push_str(current_buf, yytext);
}
|