initial commit
This commit is contained in:
commit
cd097dc4f1
|
@ -0,0 +1,3 @@
|
|||
tmp
|
||||
*.o
|
||||
mount-http-dir
|
|
@ -0,0 +1,9 @@
|
|||
{
|
||||
"name": "mount-http-dir",
|
||||
"files": [ { "git": 1 } ],
|
||||
"build" : {
|
||||
"directory": "build",
|
||||
"build": "make",
|
||||
"install": "make install"
|
||||
}
|
||||
}
|
|
@ -0,0 +1,15 @@
|
|||
CC=gcc
|
||||
CFLAGS=-I. -Wall -Wextra -lgumbo -g
|
||||
DEPS =
|
||||
OBJ = main.o link.o test.o
|
||||
|
||||
%.o: %.c $(DEPS)
|
||||
$(CC) -c -o $@ $< $(CFLAGS)
|
||||
|
||||
mount-http-dir: $(OBJ)
|
||||
$(CC) -o $@ $^ $(CFLAGS)
|
||||
|
||||
.PHONY: clean
|
||||
|
||||
clean:
|
||||
rm -f *.o mount-http-dir
|
|
@ -0,0 +1,23 @@
|
|||
## Basic ideas
|
||||
# Syntax
|
||||
mount-http-directory-listing url cache mount_pt
|
||||
|
||||
# Libraries used
|
||||
libcurl libgumbo libfuse
|
||||
|
||||
|
||||
- Seek an URL
|
||||
- If fail, continue
|
||||
- Download it
|
||||
- Allocate random directory
|
||||
- Parse it
|
||||
- For each link, seek
|
||||
- if fail
|
||||
- directory
|
||||
- else
|
||||
- actual file
|
||||
|
||||
Things to write:
|
||||
1) Link parser
|
||||
2) libcurl
|
||||
3) fuser
|
|
@ -0,0 +1,546 @@
|
|||
/*****************************************************************************
|
||||
*
|
||||
* This example source code introduces a c library buffered I/O interface to
|
||||
* URL reads it supports fopen(), fread(), fgets(), feof(), fclose(),
|
||||
* rewind(). Supported functions have identical prototypes to their normal c
|
||||
* lib namesakes and are preceaded by url_ .
|
||||
*
|
||||
* Using this code you can replace your program's fopen() with url_fopen()
|
||||
* and fread() with url_fread() and it become possible to read remote streams
|
||||
* instead of (only) local files. Local files (ie those that can be directly
|
||||
* fopened) will drop back to using the underlying clib implementations
|
||||
*
|
||||
* See the main() function at the bottom that shows an app that retrieves from
|
||||
* a specified url using fgets() and fread() and saves as two output files.
|
||||
*
|
||||
* Copyright (c) 2003, 2017 Simtec Electronics
|
||||
*
|
||||
* Re-implemented by Vincent Sanders <vince@kyllikki.org> with extensive
|
||||
* reference to original curl example code
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* 3. The name of the author may not be used to endorse or promote products
|
||||
* derived from this software without specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
||||
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
||||
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
||||
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
||||
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
||||
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*
|
||||
* This example requires libcurl 7.9.7 or later.
|
||||
*/
|
||||
/* <DESC>
|
||||
* implements an fopen() abstraction allowing reading from URLs
|
||||
* </DESC>
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#ifndef WIN32
|
||||
# include <sys/time.h>
|
||||
#endif
|
||||
#include <stdlib.h>
|
||||
#include <errno.h>
|
||||
|
||||
#include <curl/curl.h>
|
||||
|
||||
enum fcurl_type_e {
|
||||
CFTYPE_NONE = 0,
|
||||
CFTYPE_FILE = 1,
|
||||
CFTYPE_CURL = 2
|
||||
};
|
||||
|
||||
struct fcurl_data
|
||||
{
|
||||
enum fcurl_type_e type; /* type of handle */
|
||||
union {
|
||||
CURL *curl;
|
||||
FILE *file;
|
||||
} handle; /* handle */
|
||||
|
||||
char *buffer; /* buffer to store cached data*/
|
||||
size_t buffer_len; /* currently allocated buffers length */
|
||||
size_t buffer_pos; /* end of data in buffer*/
|
||||
int still_running; /* Is background url fetch still in progress */
|
||||
};
|
||||
|
||||
typedef struct fcurl_data URL_FILE;
|
||||
|
||||
/* exported functions */
|
||||
URL_FILE *url_fopen(const char *url, const char *operation);
|
||||
int url_fclose(URL_FILE *file);
|
||||
int url_feof(URL_FILE *file);
|
||||
size_t url_fread(void *ptr, size_t size, size_t nmemb, URL_FILE *file);
|
||||
char *url_fgets(char *ptr, size_t size, URL_FILE *file);
|
||||
void url_rewind(URL_FILE *file);
|
||||
|
||||
/* we use a global one for convenience */
|
||||
static CURLM *multi_handle;
|
||||
|
||||
/* curl calls this routine to get more data */
|
||||
static size_t write_callback(char *buffer,
|
||||
size_t size,
|
||||
size_t nitems,
|
||||
void *userp)
|
||||
{
|
||||
char *newbuff;
|
||||
size_t rembuff;
|
||||
|
||||
URL_FILE *url = (URL_FILE *)userp;
|
||||
size *= nitems;
|
||||
|
||||
rembuff = url->buffer_len - url->buffer_pos; /* remaining space in buffer */
|
||||
|
||||
if(size > rembuff) {
|
||||
/* not enough space in buffer */
|
||||
newbuff = realloc(url->buffer, url->buffer_len + (size - rembuff));
|
||||
if(newbuff == NULL) {
|
||||
fprintf(stderr, "callback buffer grow failed\n");
|
||||
size = rembuff;
|
||||
}
|
||||
else {
|
||||
/* realloc succeeded increase buffer size*/
|
||||
url->buffer_len += size - rembuff;
|
||||
url->buffer = newbuff;
|
||||
}
|
||||
}
|
||||
|
||||
memcpy(&url->buffer[url->buffer_pos], buffer, size);
|
||||
url->buffer_pos += size;
|
||||
|
||||
return size;
|
||||
}
|
||||
|
||||
/* use to attempt to fill the read buffer up to requested number of bytes */
|
||||
static int fill_buffer(URL_FILE *file, size_t want)
|
||||
{
|
||||
fd_set fdread;
|
||||
fd_set fdwrite;
|
||||
fd_set fdexcep;
|
||||
struct timeval timeout;
|
||||
int rc;
|
||||
CURLMcode mc; /* curl_multi_fdset() return code */
|
||||
|
||||
/* only attempt to fill buffer if transactions still running and buffer
|
||||
* doesn't exceed required size already
|
||||
*/
|
||||
if((!file->still_running) || (file->buffer_pos > want))
|
||||
return 0;
|
||||
|
||||
/* attempt to fill buffer */
|
||||
do {
|
||||
int maxfd = -1;
|
||||
long curl_timeo = -1;
|
||||
|
||||
FD_ZERO(&fdread);
|
||||
FD_ZERO(&fdwrite);
|
||||
FD_ZERO(&fdexcep);
|
||||
|
||||
/* set a suitable timeout to fail on */
|
||||
timeout.tv_sec = 60; /* 1 minute */
|
||||
timeout.tv_usec = 0;
|
||||
|
||||
curl_multi_timeout(multi_handle, &curl_timeo);
|
||||
if(curl_timeo >= 0) {
|
||||
timeout.tv_sec = curl_timeo / 1000;
|
||||
if(timeout.tv_sec > 1)
|
||||
timeout.tv_sec = 1;
|
||||
else
|
||||
timeout.tv_usec = (curl_timeo % 1000) * 1000;
|
||||
}
|
||||
|
||||
/* get file descriptors from the transfers */
|
||||
mc = curl_multi_fdset(multi_handle, &fdread, &fdwrite, &fdexcep, &maxfd);
|
||||
|
||||
if(mc != CURLM_OK) {
|
||||
fprintf(stderr, "curl_multi_fdset() failed, code %d.\n", mc);
|
||||
break;
|
||||
}
|
||||
|
||||
/* On success the value of maxfd is guaranteed to be >= -1. We call
|
||||
select(maxfd + 1, ...); specially in case of (maxfd == -1) there are
|
||||
no fds ready yet so we call select(0, ...) --or Sleep() on Windows--
|
||||
to sleep 100ms, which is the minimum suggested value in the
|
||||
curl_multi_fdset() doc. */
|
||||
|
||||
if(maxfd == -1) {
|
||||
#ifdef _WIN32
|
||||
Sleep(100);
|
||||
rc = 0;
|
||||
#else
|
||||
/* Portable sleep for platforms other than Windows. */
|
||||
struct timeval wait = { 0, 100 * 1000 }; /* 100ms */
|
||||
rc = select(0, NULL, NULL, NULL, &wait);
|
||||
#endif
|
||||
}
|
||||
else {
|
||||
/* Note that on some platforms 'timeout' may be modified by select().
|
||||
If you need access to the original value save a copy beforehand. */
|
||||
rc = select(maxfd + 1, &fdread, &fdwrite, &fdexcep, &timeout);
|
||||
}
|
||||
|
||||
switch(rc) {
|
||||
case -1:
|
||||
/* select error */
|
||||
break;
|
||||
|
||||
case 0:
|
||||
default:
|
||||
/* timeout or readable/writable sockets */
|
||||
curl_multi_perform(multi_handle, &file->still_running);
|
||||
break;
|
||||
}
|
||||
} while(file->still_running && (file->buffer_pos < want));
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* use to remove want bytes from the front of a files buffer */
|
||||
static int use_buffer(URL_FILE *file, size_t want)
|
||||
{
|
||||
/* sort out buffer */
|
||||
if((file->buffer_pos - want) <= 0) {
|
||||
/* ditch buffer - write will recreate */
|
||||
free(file->buffer);
|
||||
file->buffer = NULL;
|
||||
file->buffer_pos = 0;
|
||||
file->buffer_len = 0;
|
||||
}
|
||||
else {
|
||||
/* move rest down make it available for later */
|
||||
memmove(file->buffer,
|
||||
&file->buffer[want],
|
||||
(file->buffer_pos - want));
|
||||
|
||||
file->buffer_pos -= want;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
URL_FILE *url_fopen(const char *url, const char *operation)
|
||||
{
|
||||
/* this code could check for URLs or types in the 'url' and
|
||||
basically use the real fopen() for standard files */
|
||||
|
||||
URL_FILE *file;
|
||||
(void)operation;
|
||||
|
||||
file = calloc(1, sizeof(URL_FILE));
|
||||
if(!file)
|
||||
return NULL;
|
||||
|
||||
file->handle.file = fopen(url, operation);
|
||||
if(file->handle.file)
|
||||
file->type = CFTYPE_FILE; /* marked as URL */
|
||||
|
||||
else {
|
||||
file->type = CFTYPE_CURL; /* marked as URL */
|
||||
file->handle.curl = curl_easy_init();
|
||||
|
||||
curl_easy_setopt(file->handle.curl, CURLOPT_URL, url);
|
||||
curl_easy_setopt(file->handle.curl, CURLOPT_WRITEDATA, file);
|
||||
curl_easy_setopt(file->handle.curl, CURLOPT_VERBOSE, 0L);
|
||||
curl_easy_setopt(file->handle.curl, CURLOPT_WRITEFUNCTION, write_callback);
|
||||
|
||||
if(!multi_handle)
|
||||
multi_handle = curl_multi_init();
|
||||
|
||||
curl_multi_add_handle(multi_handle, file->handle.curl);
|
||||
|
||||
/* lets start the fetch */
|
||||
curl_multi_perform(multi_handle, &file->still_running);
|
||||
|
||||
if((file->buffer_pos == 0) && (!file->still_running)) {
|
||||
/* if still_running is 0 now, we should return NULL */
|
||||
|
||||
/* make sure the easy handle is not in the multi handle anymore */
|
||||
curl_multi_remove_handle(multi_handle, file->handle.curl);
|
||||
|
||||
/* cleanup */
|
||||
curl_easy_cleanup(file->handle.curl);
|
||||
|
||||
free(file);
|
||||
|
||||
file = NULL;
|
||||
}
|
||||
}
|
||||
return file;
|
||||
}
|
||||
|
||||
int url_fclose(URL_FILE *file)
|
||||
{
|
||||
int ret = 0;/* default is good return */
|
||||
|
||||
switch(file->type) {
|
||||
case CFTYPE_FILE:
|
||||
ret = fclose(file->handle.file); /* passthrough */
|
||||
break;
|
||||
|
||||
case CFTYPE_CURL:
|
||||
/* make sure the easy handle is not in the multi handle anymore */
|
||||
curl_multi_remove_handle(multi_handle, file->handle.curl);
|
||||
|
||||
/* cleanup */
|
||||
curl_easy_cleanup(file->handle.curl);
|
||||
break;
|
||||
|
||||
default: /* unknown or supported type - oh dear */
|
||||
ret = EOF;
|
||||
errno = EBADF;
|
||||
break;
|
||||
}
|
||||
|
||||
free(file->buffer);/* free any allocated buffer space */
|
||||
free(file);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
int url_feof(URL_FILE *file)
|
||||
{
|
||||
int ret = 0;
|
||||
|
||||
switch(file->type) {
|
||||
case CFTYPE_FILE:
|
||||
ret = feof(file->handle.file);
|
||||
break;
|
||||
|
||||
case CFTYPE_CURL:
|
||||
if((file->buffer_pos == 0) && (!file->still_running))
|
||||
ret = 1;
|
||||
break;
|
||||
|
||||
default: /* unknown or supported type - oh dear */
|
||||
ret = -1;
|
||||
errno = EBADF;
|
||||
break;
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
|
||||
size_t url_fread(void *ptr, size_t size, size_t nmemb, URL_FILE *file)
|
||||
{
|
||||
size_t want;
|
||||
|
||||
switch(file->type) {
|
||||
case CFTYPE_FILE:
|
||||
want = fread(ptr, size, nmemb, file->handle.file);
|
||||
break;
|
||||
|
||||
case CFTYPE_CURL:
|
||||
want = nmemb * size;
|
||||
|
||||
fill_buffer(file, want);
|
||||
|
||||
/* check if there's data in the buffer - if not fill_buffer()
|
||||
* either errored or EOF */
|
||||
if(!file->buffer_pos)
|
||||
return 0;
|
||||
|
||||
/* ensure only available data is considered */
|
||||
if(file->buffer_pos < want)
|
||||
want = file->buffer_pos;
|
||||
|
||||
/* xfer data to caller */
|
||||
memcpy(ptr, file->buffer, want);
|
||||
|
||||
use_buffer(file, want);
|
||||
|
||||
want = want / size; /* number of items */
|
||||
break;
|
||||
|
||||
default: /* unknown or supported type - oh dear */
|
||||
want = 0;
|
||||
errno = EBADF;
|
||||
break;
|
||||
|
||||
}
|
||||
return want;
|
||||
}
|
||||
|
||||
char *url_fgets(char *ptr, size_t size, URL_FILE *file)
|
||||
{
|
||||
size_t want = size - 1;/* always need to leave room for zero termination */
|
||||
size_t loop;
|
||||
|
||||
switch(file->type) {
|
||||
case CFTYPE_FILE:
|
||||
ptr = fgets(ptr, (int)size, file->handle.file);
|
||||
break;
|
||||
|
||||
case CFTYPE_CURL:
|
||||
fill_buffer(file, want);
|
||||
|
||||
/* check if there's data in the buffer - if not fill either errored or
|
||||
* EOF */
|
||||
if(!file->buffer_pos)
|
||||
return NULL;
|
||||
|
||||
/* ensure only available data is considered */
|
||||
if(file->buffer_pos < want)
|
||||
want = file->buffer_pos;
|
||||
|
||||
/*buffer contains data */
|
||||
/* look for newline or eof */
|
||||
for(loop = 0; loop < want; loop++) {
|
||||
if(file->buffer[loop] == '\n') {
|
||||
want = loop + 1;/* include newline */
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
/* xfer data to caller */
|
||||
memcpy(ptr, file->buffer, want);
|
||||
ptr[want] = 0;/* always null terminate */
|
||||
|
||||
use_buffer(file, want);
|
||||
|
||||
break;
|
||||
|
||||
default: /* unknown or supported type - oh dear */
|
||||
ptr = NULL;
|
||||
errno = EBADF;
|
||||
break;
|
||||
}
|
||||
|
||||
return ptr;/*success */
|
||||
}
|
||||
|
||||
void url_rewind(URL_FILE *file)
|
||||
{
|
||||
switch(file->type) {
|
||||
case CFTYPE_FILE:
|
||||
rewind(file->handle.file); /* passthrough */
|
||||
break;
|
||||
|
||||
case CFTYPE_CURL:
|
||||
/* halt transaction */
|
||||
curl_multi_remove_handle(multi_handle, file->handle.curl);
|
||||
|
||||
/* restart */
|
||||
curl_multi_add_handle(multi_handle, file->handle.curl);
|
||||
|
||||
/* ditch buffer - write will recreate - resets stream pos*/
|
||||
free(file->buffer);
|
||||
file->buffer = NULL;
|
||||
file->buffer_pos = 0;
|
||||
file->buffer_len = 0;
|
||||
|
||||
break;
|
||||
|
||||
default: /* unknown or supported type - oh dear */
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
#define FGETSFILE "fgets.test"
|
||||
#define FREADFILE "fread.test"
|
||||
#define REWINDFILE "rewind.test"
|
||||
|
||||
/* Small main program to retrieve from a url using fgets and fread saving the
|
||||
* output to two test files (note the fgets method will corrupt binary files if
|
||||
* they contain 0 chars */
|
||||
int main(int argc, char *argv[])
|
||||
{
|
||||
URL_FILE *handle;
|
||||
FILE *outf;
|
||||
|
||||
size_t nread;
|
||||
char buffer[256];
|
||||
const char *url;
|
||||
|
||||
if(argc < 2)
|
||||
url = "http://192.168.7.3/testfile";/* default to testurl */
|
||||
else
|
||||
url = argv[1];/* use passed url */
|
||||
|
||||
/* copy from url line by line with fgets */
|
||||
outf = fopen(FGETSFILE, "wb+");
|
||||
if(!outf) {
|
||||
perror("couldn't open fgets output file\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
handle = url_fopen(url, "r");
|
||||
if(!handle) {
|
||||
printf("couldn't url_fopen() %s\n", url);
|
||||
fclose(outf);
|
||||
return 2;
|
||||
}
|
||||
|
||||
while(!url_feof(handle)) {
|
||||
url_fgets(buffer, sizeof(buffer), handle);
|
||||
fwrite(buffer, 1, strlen(buffer), outf);
|
||||
}
|
||||
|
||||
url_fclose(handle);
|
||||
|
||||
fclose(outf);
|
||||
|
||||
|
||||
/* Copy from url with fread */
|
||||
outf = fopen(FREADFILE, "wb+");
|
||||
if(!outf) {
|
||||
perror("couldn't open fread output file\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
handle = url_fopen("testfile", "r");
|
||||
if(!handle) {
|
||||
printf("couldn't url_fopen() testfile\n");
|
||||
fclose(outf);
|
||||
return 2;
|
||||
}
|
||||
|
||||
do {
|
||||
nread = url_fread(buffer, 1, sizeof(buffer), handle);
|
||||
fwrite(buffer, 1, nread, outf);
|
||||
} while(nread);
|
||||
|
||||
url_fclose(handle);
|
||||
|
||||
fclose(outf);
|
||||
|
||||
|
||||
/* Test rewind */
|
||||
outf = fopen(REWINDFILE, "wb+");
|
||||
if(!outf) {
|
||||
perror("couldn't open fread output file\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
handle = url_fopen("testfile", "r");
|
||||
if(!handle) {
|
||||
printf("couldn't url_fopen() testfile\n");
|
||||
fclose(outf);
|
||||
return 2;
|
||||
}
|
||||
|
||||
nread = url_fread(buffer, 1, sizeof(buffer), handle);
|
||||
fwrite(buffer, 1, nread, outf);
|
||||
url_rewind(handle);
|
||||
|
||||
buffer[0]='\n';
|
||||
fwrite(buffer, 1, 1, outf);
|
||||
|
||||
nread = url_fread(buffer, 1, sizeof(buffer), handle);
|
||||
fwrite(buffer, 1, nread, outf);
|
||||
|
||||
url_fclose(handle);
|
||||
|
||||
fclose(outf);
|
||||
|
||||
return 0;/* all done */
|
||||
}
|
|
@ -0,0 +1,136 @@
|
|||
#include <ctype.h>
|
||||
|
||||
#include "link.h"
|
||||
#include "string.h"
|
||||
|
||||
static char linktype_to_char(linktype t)
|
||||
{
|
||||
switch (t) {
|
||||
case LINK_DIR :
|
||||
return 'D';
|
||||
case LINK_FILE :
|
||||
return 'F';
|
||||
case LINK_UNKNOWN :
|
||||
return 'U';
|
||||
default :
|
||||
return 'E';
|
||||
}
|
||||
}
|
||||
|
||||
void linklist_print(ll_t *links)
|
||||
{
|
||||
for (int i = 0; i < links->num; i++) {
|
||||
fprintf(stderr, "%d %c %s\n",
|
||||
i,
|
||||
linktype_to_char(links->type[i]),
|
||||
links->link[i]);
|
||||
}
|
||||
}
|
||||
|
||||
ll_t *linklist_new()
|
||||
{
|
||||
ll_t *links = malloc(sizeof(ll_t));
|
||||
links->num = 0;
|
||||
links->link = NULL;
|
||||
links->type = NULL;
|
||||
return links;
|
||||
}
|
||||
|
||||
static int is_valid_link(const char *n)
|
||||
{
|
||||
/* The link name has to start with alphanumerical character */
|
||||
if (!isalnum(n[0])) {
|
||||
return 0;
|
||||
}
|
||||
/* check for http:// and https:// */
|
||||
int c = strlen(n);
|
||||
if (c > 5) {
|
||||
if (n[0] == 'h' && n[1] == 't' && n[2] == 't' && n[3] == 'p') {
|
||||
if ((n[4] == ':' && n[5] == '/' && n[6] == '/') ||
|
||||
(n[4] == 's' && n[5] == ':' && n[6] == '/' && n[7] == '/')) {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
|
||||
/*
|
||||
* Shamelessly copied and pasted from:
|
||||
* https://github.com/google/gumbo-parser/blob/master/examples/find_links.cc
|
||||
*/
|
||||
void html_to_linklist(GumboNode *node, ll_t *links)
|
||||
{
|
||||
if (node->type != GUMBO_NODE_ELEMENT) {
|
||||
return;
|
||||
}
|
||||
GumboAttribute* href;
|
||||
|
||||
if (node->v.element.tag == GUMBO_TAG_A &&
|
||||
(href = gumbo_get_attribute(&node->v.element.attributes, "href"))) {
|
||||
/* if it is valid, copy the link onto the heap */
|
||||
if (is_valid_link(href->value)) {
|
||||
links->num++;
|
||||
if (!links->link) {
|
||||
links->link = malloc(sizeof(char *));
|
||||
links->type = malloc(sizeof(linktype *));
|
||||
} else {
|
||||
links->link = realloc(links->link, links->num * sizeof(char *));
|
||||
links->type = realloc(links->type,
|
||||
links->num * sizeof(linktype *));
|
||||
}
|
||||
int i = links->num - 1;
|
||||
links->link[i] = malloc(strlen(href->value) * sizeof(char *));
|
||||
strcpy(links->link[i], href->value);
|
||||
links->type[i] = LINK_UNKNOWN;
|
||||
}
|
||||
}
|
||||
|
||||
/* Note the recursive call, lol. */
|
||||
GumboVector *children = &node->v.element.children;
|
||||
for (size_t i = 0; i < children->length; ++i) {
|
||||
html_to_linklist((GumboNode*)children->data[i], links);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
void linklist_free(ll_t *links)
|
||||
{
|
||||
for (int i = 0; i < links->num; i++) {
|
||||
free(links->link[i]);
|
||||
}
|
||||
free(links->type);
|
||||
free(links);
|
||||
}
|
||||
|
||||
/* the upper level */
|
||||
char *url_upper(const char *url)
|
||||
{
|
||||
const char *pt = strrchr(url, '/');
|
||||
/* +1 for the '/' */
|
||||
size_t len = pt - url + 1;
|
||||
char *str = malloc(len* sizeof(char));
|
||||
strncpy(str, url, len);
|
||||
str[len] = '\0';
|
||||
return str;
|
||||
}
|
||||
|
||||
/* append url */
|
||||
char *url_append(const char *url, const char *sublink)
|
||||
{
|
||||
int needs_separator = 0;
|
||||
if (url[strlen(url)-1] != '/') {
|
||||
needs_separator = 1;
|
||||
}
|
||||
|
||||
char *str;
|
||||
size_t ul = strlen(url);
|
||||
size_t sl = strlen(sublink);
|
||||
str = calloc(ul + sl + needs_separator, sizeof(char));
|
||||
strncpy(str, url, ul);
|
||||
if (needs_separator) {
|
||||
str[ul] = '/';
|
||||
}
|
||||
strncat(str, sublink, sl);
|
||||
return str;
|
||||
}
|
|
@ -0,0 +1,40 @@
|
|||
#ifndef LINK_H
|
||||
#define LINK_H
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
#include <gumbo.h>
|
||||
/* \brief the link type */
|
||||
typedef enum {
|
||||
LINK_DIR,
|
||||
LINK_FILE,
|
||||
LINK_UNKNOWN
|
||||
} linktype;
|
||||
|
||||
/* \brief link list data type */
|
||||
typedef struct {
|
||||
int num;
|
||||
char **link;
|
||||
linktype *type;
|
||||
} ll_t;
|
||||
|
||||
/* \brief make a new link list */
|
||||
ll_t *linklist_new();
|
||||
|
||||
/* \brief print a link list */
|
||||
void linklist_print(ll_t *links);
|
||||
|
||||
/* \brief convert a html page to a link list */
|
||||
void html_to_linklist(GumboNode *node, ll_t *links);
|
||||
|
||||
/* \brief free a link list */
|
||||
void linklist_free(ll_t *links);
|
||||
|
||||
/* \brief the upper level */
|
||||
/* \warning does not check if you have reached the base level! */
|
||||
char *url_upper(const char *url);
|
||||
|
||||
/* \brief append url */
|
||||
char *url_append(const char *url, const char *sublink);
|
||||
|
||||
#endif
|
|
@ -0,0 +1,13 @@
|
|||
#include <errno.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "test.h"
|
||||
|
||||
|
||||
int main(int argc, char** argv) {
|
||||
gumbo_test(argc, argv);
|
||||
url_test();
|
||||
return 0;
|
||||
}
|
|
@ -0,0 +1,53 @@
|
|||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <errno.h>
|
||||
|
||||
#include "link.h"
|
||||
#include "test.h"
|
||||
|
||||
void url_test()
|
||||
{
|
||||
printf("--- start of url_test ---\n");
|
||||
char *url1 = "http://www.google.com/";
|
||||
char *url2 = "http://www.google.com";
|
||||
char *cat_url1 = url_append(url1, "fangfufu");
|
||||
char *cat_url2 = url_append(url2, "fangfufu");
|
||||
printf("%d %s\n", (int) strlen(cat_url1), cat_url1);
|
||||
printf("%d %s\n", (int) strlen(cat_url2), cat_url2);
|
||||
printf("--- end of url_test ---\n\n");
|
||||
}
|
||||
|
||||
void gumbo_test(int argc, char **argv)
|
||||
{
|
||||
printf("--- start of gumbo_test ---\n");
|
||||
if (argc != 2) {
|
||||
fprintf(stderr, "Usage: find_links <html filename>.\n");
|
||||
}
|
||||
const char* filename = argv[1];
|
||||
|
||||
FILE *fp;
|
||||
fp = fopen(filename, "r");
|
||||
|
||||
if (!fp) {
|
||||
fprintf(stderr, "File %s not found!\n", filename);
|
||||
}
|
||||
|
||||
fseek(fp, 0L, SEEK_END);
|
||||
unsigned long filesize = ftell(fp);
|
||||
rewind(fp);
|
||||
|
||||
char* contents = (char*) malloc(sizeof(char) * filesize);
|
||||
if (fread(contents, 1, filesize, fp) != filesize) {
|
||||
fprintf(stderr, "Read error, %s\n", strerror(errno));
|
||||
}
|
||||
fclose(fp);
|
||||
|
||||
GumboOutput* output = gumbo_parse(contents);
|
||||
ll_t *links = linklist_new();
|
||||
html_to_linklist(output->root, links);
|
||||
gumbo_destroy_output(&kGumboDefaultOptions, output);
|
||||
linklist_print(links);
|
||||
linklist_free(links);
|
||||
printf("--- end of gumbo_test ---\n\n");
|
||||
}
|
Loading…
Reference in New Issue