summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/Makefile.am7
-rw-r--r--src/config.c168
-rw-r--r--src/download.c228
-rw-r--r--src/getht.c394
-rw-r--r--src/getht.h47
-rw-r--r--src/issue.h77
-rw-r--r--src/issuemem.c174
-rw-r--r--src/mediarev.c150
-rw-r--r--src/mediaxml.c246
-rw-r--r--src/tocxml.c264
-rw-r--r--src/version.h22
-rw-r--r--src/xml.c62
12 files changed, 1839 insertions, 0 deletions
diff --git a/src/Makefile.am b/src/Makefile.am
new file mode 100644
index 0000000..0bf3452
--- /dev/null
+++ b/src/Makefile.am
@@ -0,0 +1,7 @@
+## A simple file to process with Automake, to produce Makefile.in
+
+bin_PROGRAMS = getht
+
+getht_SOURCES = config.c download.c getht.c issuemem.c \
+ mediarev.c mediaxml.c tocxml.c xml.c \
+ getht.h issue.h version.h
diff --git a/src/config.c b/src/config.c
new file mode 100644
index 0000000..57807b1
--- /dev/null
+++ b/src/config.c
@@ -0,0 +1,168 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "getht.h"
+
+extern proxytype proxy_type;
+extern char proxy_addr[STR_MAX];
+extern long proxy_port;
+extern proxyauth proxy_auth;
+extern char proxy_user[STR_MAX];
+extern char proxy_pass[STR_MAX];
+
+int loadconfig(char * htde_path, char * issue_path, int * update)
+/* Loads variables from config file to extern and passed
+ * variables. */
+{
+ FILE * config_file;
+ char filepath[STR_MAX];
+
+ snprintf(filepath, STR_MAX, "%s/config.ini", htde_path);
+
+ if((config_file = fopen(filepath,"r")) == NULL)
+ {
+ fprintf(stderr,"Cannot open file %s for reading.\n",filepath);
+ return 1;
+ }
+
+ char parameter[80], option[80];
+ while(!feof(config_file))
+ {
+ fscanf(config_file, "%s = %s", option, parameter);
+
+ if(option[0] == '#'); /* ignore lines beginning with a hash */
+ else if(!strcmp(option, "issuepath"))
+ strncpy(issue_path, parameter, STR_MAX);
+ else if(!strcmp(option, "startup_check"))
+ *update = atoi(parameter);
+ else if(!strcmp(option, "proxy_type"))
+ {
+ if(!strcmp(parameter, "http"))
+ proxy_type = HTTP;
+ else if(!strcmp(parameter, "socks4"))
+ proxy_type = SOCKS4;
+ else if(!strcmp(parameter, "socks5"))
+ proxy_type = SOCKS5;
+ else
+ fprintf(stderr,
+ "Proxy type %s not known, please use either http, socks4 or socks5",
+ parameter);
+ }
+ else if(!strcmp(option, "proxy_address"))
+ strncpy(proxy_addr, parameter, STR_MAX);
+ else if(!strcmp(option, "proxy_port"))
+ proxy_port = (long) atoi(parameter);
+ else if(!strcmp(option, "proxy_auth"))
+ {
+ if(!strcmp(parameter, "basic"))
+ proxy_auth = BASIC;
+ else if(!strcmp(parameter, "digest"))
+ proxy_auth = DIGEST;
+ else if(!strcmp(parameter, "ntlm"))
+ proxy_auth = NTLM;
+ else
+ fprintf(stderr,
+ "Proxy authentication method %s not known, please use basic, digest or ntlm",
+ parameter);
+ }
+ else if(!strcmp(option, "proxy_user"))
+ strncpy(proxy_user, parameter, STR_MAX);
+ else if(!strcmp(option, "proxy_pass"))
+ strncpy(proxy_pass, parameter, STR_MAX);
+ else
+ fprintf(stderr, "Option '%s' not recognised, ignoring\n", option);
+ }
+
+ return 0;
+}
+
+int writefreshconfig(char * htde_path, char * issue_path, int * update)
+/* Write a new config file according to extern and passed variables. */
+{
+ FILE * config_file;
+ char filepath[STR_MAX];
+
+ snprintf(filepath, STR_MAX, "%s/config.ini", htde_path);
+
+ if((config_file = fopen(filepath,"w")) == NULL)
+ {
+ fprintf(stderr,"Cannot open file %s for writing.\n",filepath);
+ return 1;
+ }
+ else
+ fprintf(stdout,"Writing a fresh config file to %s.\n",filepath);
+
+ if(issue_path[0])
+ fprintf(config_file, "%s = %s\n", "issuepath", issue_path);
+ if(update)
+ fprintf(config_file, "%s = %i\n", "startup_check", *update);
+ if(proxy_type != NONE)
+ {
+ if(proxy_type = HTTP)
+ fprintf(config_file, "%s = %s\n", "proxy_type", "http");
+ else if(proxy_type = SOCKS4)
+ fprintf(config_file, "%s = %s\n", "proxy_type", "socks4");
+ else if(proxy_type = SOCKS5)
+ fprintf(config_file, "%s = %s\n", "proxy_type", "socks5");
+ }
+ if(proxy_addr[0])
+ fprintf(config_file, "%s = %s\n", "proxy_address", proxy_addr);
+ if(proxy_port)
+ fprintf(config_file, "%s = %i\n", "proxy_port", proxy_port);
+ if(proxy_auth != NOAUTH)
+ {
+ if(proxy_auth = BASIC)
+ fprintf(config_file, "%s = %s\n", "proxy_auth", "basic");
+ else if(proxy_auth = DIGEST)
+ fprintf(config_file, "%s = %s\n", "proxy_auth", "digest");
+ else if(proxy_auth = NTLM)
+ fprintf(config_file, "%s = %s\n", "proxy_auth", "ntlm");
+ }
+ if(proxy_user[0])
+ fprintf(config_file, "%s = %s\n", "proxy_user", proxy_user);
+ if(proxy_pass[0])
+ fprintf(config_file, "%s = %s\n", "proxy_pass", proxy_pass);
+
+ return 0;
+}
+
+int updateconfig(char * htde_path, char * issue_path, int * update)
+/* Read existing config file, and rewrite any variables which differ
+ * in memory. */
+{
+ FILE * config_file;
+ char filepath[STR_MAX];
+
+ snprintf(filepath, STR_MAX, "%s/config.ini", htde_path);
+
+ if((config_file = fopen(filepath,"rw")) == NULL)
+ {
+ fprintf(stderr,"Cannot open file %s for reading/writing.\n",filepath);
+ return 1;
+ }
+
+ fprintf(stderr,"Not yet implemented.\n");
+
+ return 1;
+}
diff --git a/src/download.c b/src/download.c
new file mode 100644
index 0000000..1108b6d
--- /dev/null
+++ b/src/download.c
@@ -0,0 +1,228 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <curl/curl.h>
+#include <curl/types.h>
+#include <curl/easy.h>
+
+#include "getht.h"
+#include "issue.h"
+
+int read_func(void *ptr, size_t size, size_t nmemb, FILE *stream)
+ { return fread(ptr, size, nmemb, stream); }
+int write_func(void *ptr, size_t size, size_t nmemb, FILE *stream)
+ { return fwrite(ptr, size, nmemb, stream); }
+int update_progress(void *data, double dltotal, double dlnow,
+ double ultotal, double ulnow);
+
+extern proxytype proxy_type;
+extern char proxy_addr[STR_MAX];
+extern long proxy_port;
+extern proxyauth proxy_auth;
+extern char proxy_user[STR_MAX];
+extern char proxy_pass[STR_MAX];
+extern CURL *main_curl_handle;
+
+int save_file(CURL *curl_handle, char *url, char *filepath)
+/* Save the file *url to *filepath */
+{
+ printf("Downloading %s\n",url);
+
+ if(curl_handle == NULL)
+ curl_handle = main_curl_handle;
+
+ if(curl_handle) {
+ FILE *file;
+ if((file = fopen(filepath,"w")) == NULL)
+ {
+ fprintf(stderr,"Error: cannot open file %s for writing.\n",filepath);
+ return 1;
+ }
+
+ curl_easy_setopt(curl_handle, CURLOPT_URL, url);
+ curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION, write_func);
+ curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, file);
+ curl_easy_setopt(curl_handle, CURLOPT_READFUNCTION, read_func);
+
+ if(proxy_type != NONE)
+ {
+ if(proxy_type == HTTP)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
+ else if(proxy_type == SOCKS4)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS4);
+ else if(proxy_type == SOCKS5)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5);
+
+ curl_easy_setopt(curl_handle, CURLOPT_PROXY, proxy_addr);
+
+ if(proxy_port)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYPORT, proxy_port);
+
+ if(proxy_auth != NOAUTH)
+ {
+ if(proxy_auth == BASIC)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYAUTH, CURLAUTH_BASIC);
+ else if(proxy_auth == DIGEST)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYAUTH, CURLAUTH_DIGEST);
+ else if(proxy_auth == NTLM)
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYAUTH, CURLAUTH_NTLM);
+
+ if(proxy_user[0] && proxy_pass[0])
+ {
+ char userpass[STR_MAX];
+ snprintf(userpass, STR_MAX, "%s:%s", proxy_user, proxy_pass);
+ curl_easy_setopt(curl_handle, CURLOPT_PROXYUSERPWD, userpass);
+ }
+ }
+ }
+
+ curl_easy_setopt(curl_handle, CURLOPT_NOPROGRESS, 0);
+ curl_easy_setopt(curl_handle, CURLOPT_PROGRESSFUNCTION, update_progress);
+
+ if(curl_easy_perform(curl_handle))
+ {
+ remove(filepath);
+ fprintf(stderr,"Error, could not download %s\n",url);
+ return 1;
+ }
+
+/* double d;
+ curl_easy_getinfo(curl_handle, CURLINFO_SIZE_DOWNLOAD, &d);
+ printf("Total downloaded: %lf\n",d);
+
+ curl_easy_getinfo(curl_handle, CURLINFO_SPEED_DOWNLOAD, &d);
+ printf("Average speed downloaded: %lf\n",d);
+
+ curl_easy_getinfo(curl_handle, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &d);
+ printf("Content Length: %lf\n",d);
+*/
+ fclose(file);
+
+ printf("\n");
+ }
+ else {
+ fprintf(stderr,"Error: curl failed to initialise.\n");
+ printf("Could not download %s\n",url);
+ return 1;
+ }
+ return 0;
+}
+
+int update_progress(void *data, double dltotal, double dlnow,
+ double ultotal, double ulnow)
+/* Print status information */
+{
+ double frac;
+ frac = 100 * dlnow / dltotal;
+ printf("\rDownload progress: %3.0lf%% ", frac);
+ fflush(stdout);
+
+ return 0;
+}
+
+void downloadissue(CURL *curl_handle, char * directory, iss * issue, int force)
+/* Download issue pointed to */
+{
+ sec * cur_section;
+ char newdir[STR_MAX];
+ char filename[STR_MAX];
+ FILE * testfile;
+
+ snprintf(newdir,STR_MAX,"%s/%i_%i-%i",directory,
+ issue->date.year,issue->date.firstmonth,issue->date.lastmonth);
+
+ printf("Downloading issue entitled '%s' to '%s'\n",issue->title,newdir);
+
+ if(!opendir(newdir))
+ if(mkdir(newdir, S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH))
+ {
+ printf("Please enter the path of a directory to save issues in: ");
+ scanf("%s", newdir); /* TODO: incorporate tab-completion */
+ }
+
+ int count;
+ for(count = 0; count <= issue->no_of_sections; count++)
+ {
+ cur_section = issue->section[count];
+
+ snprintf(filename,STR_MAX,"%s/section_%i.pdf", newdir, cur_section->number);
+ if(!force){
+ testfile = fopen(filename, "r");
+ if(!testfile)
+ save_file(curl_handle, cur_section->uri, filename);
+ else
+ {
+ fclose(testfile);
+ printf("Skipping download of section %i\n", cur_section->number);
+ }
+ }
+ else
+ save_file(curl_handle, cur_section->uri, filename);
+ }
+}
+
+void downloadmedia(CURL * curl_handle, char * directory, med * media, int force)
+/* Download media pointed to. */
+{
+ char newdir[STR_MAX], filename[STR_MAX], fn[STR_MAX];
+ FILE * testfile;
+
+ /* for the moment just save to down/media, in future save to issue directories
+ * (regardless of if they're occupied) */
+ snprintf(newdir,STR_MAX,"%s/%s",directory,"media");
+
+ if(!opendir(newdir))
+ if(mkdir(newdir, S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH))
+ {
+ printf("Please enter the path of a directory to save media in: ");
+ scanf("%s", newdir); /* TODO: incorporate GETTEXT */
+ }
+
+ /* get the position of the final forwardslash of the uri */
+ int slashpos;
+ for(slashpos=strlen(media->uri);
+ slashpos>=0 && media->uri[slashpos] != '/';
+ slashpos--);
+
+ /* copy from there to fn */
+ int tmp;
+ for(tmp=0, slashpos++; media->uri[slashpos]; tmp++, slashpos++)
+ fn[tmp] = media->uri[slashpos];
+ fn[tmp] = '\0';
+
+ snprintf(filename,STR_MAX,"%s/%s", newdir, fn);
+
+ if(!force){
+ testfile = fopen(filename, "r");
+ if(!testfile)
+ save_file(curl_handle, media->uri, filename);
+ else
+ {
+ fclose(testfile);
+ printf("Skipping download of media item %s\n", media->title);
+ }
+ }
+ else
+ save_file(curl_handle, media->uri, filename);
+}
diff --git a/src/getht.c b/src/getht.c
new file mode 100644
index 0000000..5d2c39c
--- /dev/null
+++ b/src/getht.c
@@ -0,0 +1,394 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <getopt.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <curl/curl.h>
+
+#include "version.h"
+#include "issue.h"
+#include "getht.h"
+
+int update_contents_files();
+
+med * findnewestmed(iss ** issue, int no_of_issues);
+
+void show_iss_struct(iss ** issue, int no_of_issues);
+
+void showusage();
+
+proxytype proxy_type; char proxy_addr[STR_MAX]; long proxy_port;
+proxyauth proxy_auth;
+char proxy_user[STR_MAX]; char proxy_pass[STR_MAX];
+char issue_xml[STR_MAX]; char media_xml[STR_MAX]; char media_rev[STR_MAX];
+CURL *main_curl_handle;
+
+int main(int argc, char *argv[])
+{
+ char getht_path[STR_MAX];
+ char save_path[STR_MAX];
+
+ /* Define & set up paths */
+ snprintf(getht_path,STR_MAX,"%s/.getht",getenv("HOME"));
+
+ if(!opendir(getht_path))
+ if(mkdir(getht_path, S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH))
+ {
+ fprintf(stderr,"Cannot open/create directory %s\n",getht_path);
+ printf("Please enter the path of a directory to save settings in: ");
+ scanf("%s", getht_path);
+ }
+
+ snprintf(issue_xml,STR_MAX,"%s/%s",getht_path,ISS_XML_FILE);
+ snprintf(media_xml,STR_MAX, "%s/%s", getht_path, MED_XML_FILE);
+ snprintf(media_rev,STR_MAX,"%s/%s",getht_path,MED_REVGZ_FILE);
+
+ snprintf(save_path,STR_MAX,"%s/hinduism_today",getenv("HOME"));
+
+ int downall = 0, downlatest = 0;
+ int downallmedia = 0, downlatestmedia = 0;
+ int downissue = 0, downmedia = 0;
+ int force = 0, update = 0, showstr = 0;
+ int option = 0;
+
+ proxy_type = NONE;
+ proxy_port = 0;
+ proxy_addr[0] = '\0';
+ proxy_auth = NOAUTH;
+ proxy_user[0] = '\0';
+ proxy_pass[0] = '\0';
+
+ if(loadconfig(getht_path, &save_path, &update) != 0)
+ writefreshconfig(getht_path, &save_path, &update);
+
+ if(!opendir(save_path))
+ if(mkdir(save_path, S_IRWXU | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH))
+ {
+ fprintf(stderr,"Cannot open/create directory %s",save_path);
+ printf("Please enter the path of a directory to save issues in: ");
+ scanf("%s", save_path);
+
+ updateconfig(getht_path, &save_path, NULL);
+ }
+
+ /* Parse command line options */
+ char c;
+ static struct option long_opts[] =
+ {
+ {"download-all", no_argument, 0, 'a'},
+ {"download-latest", no_argument, 0, 'd'},
+ {"download-all-media", no_argument, 0, 'm'},
+ {"download-latest-media", no_argument, 0, 'n'},
+ {"force", no_argument, 0, 'f'},
+ {"update", no_argument, 0, 'u'},
+ {"tocfile", required_argument, 0, 't'},
+ {"mediatocfile", required_argument, 0, 'x'},
+ {"help", no_argument, 0, 'h'},
+ {"version", no_argument, 0, 'v'},
+ {0, 0, 0, 0}
+ };
+ while((c = getopt_long(argc, argv, "adfhmnsuvx:t:", long_opts, NULL)) != -1) {
+ switch(c) {
+ case 'a':
+ downall = 1;
+ downissue = 1;
+ option = 1;
+ break;
+ case 'd':
+ downlatest = 1;
+ downissue = 1;
+ option = 1;
+ break;
+ case 'm':
+ downallmedia = 1;
+ downmedia = 1;
+ option = 1;
+ break;
+ case 'n':
+ downlatestmedia = 1;
+ downmedia = 1;
+ option = 1;
+ break;
+ case 'f':
+ force = 1;
+ option = 1;
+ break;
+ case 'u':
+ update = 1;
+ option = 1;
+ break;
+ case 's':
+ showstr = 1;
+ option = 1;
+ break;
+ case 't':
+ strcpy(issue_xml, strdup(optarg));
+ option = 1;
+ break;
+ case 'x':
+ strcpy(media_xml, strdup(optarg));
+ option = 1;
+ break;
+ case 'h':
+ showusage();
+ return 0;
+ break;
+ case 'v':
+ printf("GetHT version: %s\n",VERSION);
+ option = 1;
+ return 0;
+ break;
+ }
+ }
+
+ if(!option)
+ {
+ showusage();
+ return 0;
+ }
+
+ main_curl_handle = curl_easy_init();
+
+ if(update)
+ {
+ if(update_contents_files())
+ fprintf(stderr,"Could not update contents files\n");
+ }
+
+ /* Parse TOC, filling issue structure */
+
+ iss **issue;
+ int no_of_issues = -1;
+ int latest_index = -1;
+ int i;
+
+ if(downissue || showstr)
+ {
+ issue = parsetoc(issue_xml, &no_of_issues, &latest_index);
+
+ if(!issue)
+ {
+ if(!update)
+ {
+ printf("Cannot open contents file, trying to update contents\n");
+ if(update_contents_files())
+ return 1;
+ issue = parsetoc(issue_xml, &no_of_issues, &latest_index);
+ }
+ else
+ {
+ printf("Cannot open contents file, try running `getht --update`\n");
+ return 1;
+ }
+ }
+
+ if(latest_index == -1)
+ {
+ fprintf(stderr, "Error: Cannot ascertain latest issue. ");
+ fprintf(stderr, "Defaulting to first issue in contents file\n");
+ latest_index = 0;
+ }
+
+ if(downall)
+ {
+ for(i = 0; i < no_of_issues; i++)
+ downloadissue(NULL, save_path, issue[i], force);
+ }
+
+ if(downlatest)
+ downloadissue(NULL, save_path, issue[latest_index], force);
+ }
+
+ if(downmedia || showstr)
+ {
+ int newest;
+
+ issue = parsemedia(media_xml, issue, &no_of_issues);
+
+ if(!issue)
+ {
+ if(!update)
+ {
+ printf("Cannot open media contents file, trying to update contents\n");
+ if(update_contents_files())
+ return 1;
+ issue = parsemedia(media_xml, issue, &no_of_issues);
+ }
+ else
+ {
+ printf("Cannot open contents file, try running `getht --update`\n");
+ return 1;
+ }
+ }
+
+ if(downlatestmedia)
+ {
+ newest = findnewestiss(issue, no_of_issues);
+ for(i = 0; i <= issue[newest]->no_of_media; i++)
+ downloadmedia(NULL, save_path, issue[newest]->media[i], force);
+ }
+
+ if(downallmedia)
+ {
+ for(i = 0; i <= no_of_issues; i++)
+ {
+ for(newest = 0; newest <= issue[i]->no_of_media; newest++)
+ downloadmedia(NULL, save_path, issue[i]->media[newest], force);
+ }
+ }
+ }
+
+ if(showstr)
+ show_iss_struct(issue, no_of_issues);
+
+ /* Ensure curl cleans itself up */
+ curl_easy_cleanup(main_curl_handle);
+
+ return 0;
+}
+
+int update_contents_files()
+/* Returns 0 on success, 1 on failure */
+{
+ if(save_file(NULL, XML_TOC_URL, issue_xml))
+ return 1;
+
+ char isstitle[STR_MAX];
+ issdates date;
+
+ /* see if current issue's media toc has already
+ been written to the xml, if not do so */
+ if(access(issue_xml, R_OK) == 0)
+ {
+ if(cur_identifiers(issue_xml, isstitle, &date))
+ return 1;
+ }
+ else
+ return 1;
+
+ if(media_accounted_for(media_xml, &date))
+ {
+ if(save_file(NULL, MEDIA_TOC_URL, media_rev))
+ return 1;
+
+ med ** temp_med;
+ int med_no = -1;
+
+ temp_med = parsemediagz(media_rev, &med_no);
+
+ unlink(media_rev);
+
+ addmediaissue(media_xml, isstitle, &date, temp_med, med_no);
+ }
+
+ return 0;
+}
+
+void show_iss_struct(iss ** issue, int no_of_issues)
+/* Prints issue information */
+{
+ int iss_no, sec_no, med_no, it_no;
+ printf("%i Issues\n",no_of_issues);
+ for(iss_no=0;iss_no<=no_of_issues;iss_no++)
+ {
+ printf("-Issue %i-\n", (iss_no+1));
+ printf("Title:\t'%s'\n", issue[iss_no]->title);
+ printf("Preview URI:\t'%s'\n", issue[iss_no]->preview_uri);
+ printf("Months:\t'%i' - '%i'\n",issue[iss_no]->date.firstmonth,issue[iss_no]->date.lastmonth);
+ printf("Year:\t'%i'\n",issue[iss_no]->date.year);
+ printf("Number of Sections:\t'%i'\n",issue[iss_no]->no_of_sections);
+
+ for(sec_no=0; sec_no <= (issue[iss_no]->no_of_sections); sec_no++)
+ {
+ printf("\t-Section %i-\n", (sec_no));
+ printf("\tTitle:\t'%s'\n", issue[iss_no]->section[sec_no]->title);
+ printf("\tURI:\t'%s'\n", issue[iss_no]->section[sec_no]->uri);
+ printf("\tNo. of Items:\t'%i'\n", issue[iss_no]->section[sec_no]->no_of_items);
+
+ for(it_no=0; it_no <= issue[iss_no]->section[sec_no]->no_of_items; it_no++)
+ {
+ printf("\t\t-Item-\n");
+ printf("\t\tTitle:\t'%s'\n",issue[iss_no]->section[sec_no]->item[it_no]->title);
+ printf("\t\tFirst page:\t'%i'",issue[iss_no]->section[sec_no]->item[it_no]->firstpage);
+ printf("\tLast page:\t'%i'\n",issue[iss_no]->section[sec_no]->item[it_no]->lastpage);
+ }
+ it_no = 0;
+ }
+ sec_no = 0;
+
+ printf("Number of Media:\t'%i'\n",issue[iss_no]->no_of_media);
+
+ for(med_no=0; med_no <= (issue[iss_no]->no_of_media); med_no++)
+ {
+ printf("\t-Media %i-\n", (med_no));
+ printf("\tTitle:\t'%s'\n", issue[iss_no]->media[med_no]->title);
+ printf("\tURI:\t'%s'\n", issue[iss_no]->media[med_no]->uri);
+ printf("\tComment:\t'%s'\n", issue[iss_no]->media[med_no]->comment);
+ printf("\tPreview URI:\t'%s'\n", issue[iss_no]->media[med_no]->preview_uri);
+ }
+ med_no = 0;
+ }
+}
+
+int findnewestiss(iss ** issue, int no_of_issues)
+/* returns newest issue indice */
+{
+ iss * tmp_issue; issdates newest;
+ int new_iss;
+
+ new_iss = -1;
+ newest.year = 0; newest.firstmonth = 0; newest.lastmonth = 0;
+
+ int i;
+
+ for(i = 0; i <= no_of_issues; i++)
+ {
+ if(issue[i]->date.year > newest.year ||
+ (issue[i]->date.year == newest.year && issue[i]->date.firstmonth > newest.firstmonth))
+ {
+ newest.year = issue[i]->date.year;
+ newest.firstmonth = issue[i]->date.firstmonth;
+ newest.lastmonth = issue[i]->date.lastmonth;
+ new_iss = i;
+ }
+ }
+
+ return new_iss;
+}
+
+void showusage()
+{
+ printf("Usage: getht -u -a -d -m -n -f [-t tocfile] -h -v\n");
+ printf("-u | --update Update contents files\n");
+ printf("-a | --download-all Download all issues\n");
+ printf("-d | --download-latest Download latest issue\n");
+ printf("-m | --download-all-media Download all media\n");
+ printf("-n | --download-latest-media Download latest issue's media\n");
+ printf("-f | --force Force re-download of existing files\n");
+ printf("-t | --tocfile file Use alternative contents xml file\n");
+ printf("-x | --mediatocfile file Use alternative media contents xml file\n");
+ printf("-h | --help Print this help message\n");
+ printf("-v | --version Print version information\n");
+}
diff --git a/src/getht.h b/src/getht.h
new file mode 100644
index 0000000..df2b1b2
--- /dev/null
+++ b/src/getht.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#define XML_TOC_URL "http://www.hinduismtoday.com/digital/htde_toc.xml"
+#define MEDIA_TOC_URL "http://www.hinduismtoday.com/digital/htde_media-player.rev.gz"
+
+#define MED_XML_FILE "media_toc.xml"
+#define ISS_XML_FILE "htde_toc.xml"
+#define MED_REVGZ_FILE "htde_media-player.rev.gz"
+
+#define STR_MAX 512
+
+#define MAX_ISS 10
+
+typedef enum
+{
+ NONE,
+ HTTP,
+ SOCKS4,
+ SOCKS5
+} proxytype;
+
+typedef enum
+{
+ NOAUTH,
+ BASIC,
+ DIGEST,
+ NTLM,
+} proxyauth;
diff --git a/src/issue.h b/src/issue.h
new file mode 100644
index 0000000..d224dcf
--- /dev/null
+++ b/src/issue.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+/* all sizes are in bytes and are child-inclusive */
+
+typedef struct
+{
+ int year;
+ int firstmonth;
+ int lastmonth;
+} issdates;
+
+typedef struct
+{
+ int firstpage;
+ int lastpage;
+ char * title;
+} it;
+
+typedef struct
+{
+ char uri[512];
+ char title[512];
+ int number;
+ int size;
+ it ** item;
+ int no_of_items;
+} sec;
+
+typedef struct
+{
+ char uri[512];
+ char title[512];
+ char comment[512];
+ char preview_uri[512];
+ int size;
+} med;
+
+typedef struct
+{
+ char preview_uri[512];
+ char title[512];
+ int size;
+ issdates date;
+ sec ** section;
+ int no_of_sections;
+ med ** media;
+ int no_of_media;
+} iss;
+
+iss ** parsetoc(char *filepath, int * iss_no, int * latest);
+iss ** parsemedia(char * filepath, iss ** issue, int * no_of_issues);
+
+med ** parsemediagz(char * media_path, int * no_of_media);
+
+iss ** assignnew_iss(iss ** issue, int *no_of_issues);
+sec ** assignnew_sec(sec ** section, int * no_of_sections);
+it ** assignnew_it(it ** item, int * no_of_items);
+med ** assignnew_med(med ** media, int * no_of_media);
diff --git a/src/issuemem.c b/src/issuemem.c
new file mode 100644
index 0000000..3a40d7e
--- /dev/null
+++ b/src/issuemem.c
@@ -0,0 +1,174 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "issue.h"
+
+void nogo_mem()
+/* called if memory assignation fails
+ * TODO: handle freeing of memory to avoid leaks */
+{
+ fprintf(stderr, "Could not assign memory, exitting\n");
+ exit(1);
+}
+
+iss ** assignnew_iss(iss ** issue, int *no_of_issues)
+/* assign memory for new issue */
+{
+ iss ** tmp = NULL;
+
+ if(*no_of_issues < 0)
+ { /* make issue** a new array of issue pointers */
+ if( (tmp = malloc(sizeof(iss *))) == NULL )
+ nogo_mem();
+ }
+ else
+ { /* add a new pointer to issue pointer list */
+ if( (tmp = realloc(issue, sizeof(iss *) + (((*no_of_issues)+1) * sizeof(iss *)))) == NULL )
+ nogo_mem();
+ }
+
+ (*no_of_issues)++;
+
+ /* make new array item a pointer to issue */
+ if( (tmp[*no_of_issues] = malloc(sizeof(iss))) == NULL )
+ nogo_mem();
+
+ return tmp;
+}
+
+sec ** assignnew_sec(sec ** section, int *no_of_sections)
+/* assign memory for new section */
+{
+ sec ** tmp = NULL;
+
+ if(*no_of_sections < 0)
+ { /* make **section a new array of section pointers */
+ if( (tmp = malloc(sizeof(sec *))) == NULL )
+ nogo_mem();
+ }
+ else
+ { /* add a new pointer to section pointer list */
+ if( (tmp = realloc(section, sizeof(sec *) + (((*no_of_sections)+1) * sizeof(sec *)))) == NULL )
+ nogo_mem();
+ }
+
+ (*no_of_sections)++;
+
+ /* make new array item a pointer to issue */
+ if( (tmp[*no_of_sections] = malloc(sizeof(sec))) == NULL )
+ nogo_mem();
+
+ return tmp;
+}
+
+it ** assignnew_it(it ** item, int * no_of_items)
+{
+ it ** tmp = NULL;
+
+ if(*no_of_items < 0)
+ { /* make **item a new array of item pointers */
+ if( (tmp = malloc(sizeof(it *))) == NULL )
+ nogo_mem();
+ }
+ else
+ { /* add a new pointer to item pointer list */
+ if( (tmp = realloc(item, sizeof(it *) + (((*no_of_items)+1) * sizeof(it *)))) == NULL )
+ nogo_mem();
+ }
+
+ (*no_of_items)++;
+
+ /* make new array item a pointer to item */
+ if( (tmp[*no_of_items] = malloc(sizeof(it))) == NULL )
+ nogo_mem();
+
+ return tmp;
+}
+
+med ** assignnew_med(med ** media, int * no_of_media)
+{
+ med ** tmp = NULL;
+
+ if(*no_of_media < 0)
+ { /* make **section a new array of section pointers */
+ if( (tmp = malloc(sizeof(med *))) == NULL )
+ nogo_mem();
+ }
+ else
+ { /* add a new pointer to media pointer list */
+ if( (tmp = realloc(media, sizeof(med *) + (((*no_of_media)+1) * sizeof(med *)))) == NULL )
+ nogo_mem();
+ }
+
+ (*no_of_media)++;
+
+ /* make new array item a pointer to issue */
+ if( (tmp[*no_of_media] = malloc(sizeof(med))) == NULL )
+ nogo_mem();
+
+ return tmp;
+}
+
+int issuesort(iss ** issue, int no_of_issues)
+/* does a basic bubble sort, by date, returning sorted issue */
+{
+ int sortindex[no_of_issues];
+
+ int count1, count2, temp;
+
+ for(count1 = 0; count1 <= no_of_issues; count1++)
+ sortindex[count1] = count1;
+
+ /* find correct order of issues using a bubble sort */
+ for(count1 = 0; count1 <=no_of_issues; count1++)
+ {
+ for(count2 = 0; count2 < no_of_issues; count2++)
+ {
+ if(issue[sortindex[count2]]->date.year < issue[sortindex[count2+1]]->date.year)
+ {
+ temp = sortindex[count2];
+ sortindex[count2] = sortindex[count2+1];
+ sortindex[count2+1] = temp;
+ }
+ else if((issue[sortindex[count2]]->date.year == issue[sortindex[count2+1]]->date.year) &&
+ (issue[sortindex[count2]]->date.firstmonth < issue[sortindex[count2+1]]->date.firstmonth))
+ {
+ temp = sortindex[count2];
+ sortindex[count2] = sortindex[count2+1];
+ sortindex[count2+1] = temp;
+ }
+ }
+ }
+
+ iss * sortedissue[no_of_issues];
+
+ for(count1 = 0; count1 <= no_of_issues; count1++)
+ sortedissue[count1] = issue[sortindex[count1]];
+
+ for(count1 = 0; count1 <= no_of_issues; count1++)
+ issue[count1] = sortedissue[count1];
+
+ return 0;
+}
diff --git a/src/mediarev.c b/src/mediarev.c
new file mode 100644
index 0000000..e8dd3e6
--- /dev/null
+++ b/src/mediarev.c
@@ -0,0 +1,150 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This mediagz is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <zlib.h>
+
+#include "getht.h"
+#include "issue.h"
+
+int smilurl(char * smilurl, med * cur_media);
+void getquote(char * input, char * label);
+void removeleadingspace(char * cur_line);
+
+med ** parsemediagz(char * media_path, int * no_of_media)
+/* Parses gzipped adobe pagemaker files for media urls and metadata,
+ * filling media with the information. */
+{
+ char cur_line[STR_MAX];
+ gzFile mediagz;
+
+ med ** media = NULL;
+
+ strcpy(cur_line,""); /* reset cur_line */
+
+ mediagz = gzopen(media_path, "r");
+
+ med * cur_media;
+
+ while(gzeof(mediagz)==0)
+ {
+ gzgets(mediagz, cur_line, STR_MAX);
+ cur_line[strlen(cur_line)-1] = '\0'; /* get rid of trailing newline */
+
+ if(!strcmp(cur_line,"on mouseUp"))
+ {
+ strcpy(cur_line,""); /* reset cur_line */
+
+ /* assign memory for the new media */
+ media = assignnew_med(media, no_of_media);
+
+ cur_media = media[*no_of_media];
+
+ /* setup media globals */
+ cur_media->uri[0] = '\0';
+ cur_media->title[0] = '\0';
+ cur_media->comment[0] = '\0';
+ cur_media->preview_uri[0] = '\0';
+ cur_media->size = 0;
+
+ /* process rev file */
+ while(strcmp(cur_line,"end mouseUp") && gzeof(mediagz)==0)
+ {
+ strcpy(cur_line,""); /* reset cur_line */
+ gzgets(mediagz, cur_line, STR_MAX);
+ cur_line[strlen(cur_line)-1] = '\0'; /* remove trailing newline */
+
+ removeleadingspace(cur_line);
+
+ if(!strncmp(cur_line,"set the filename of player \"player1\" to \"",41))
+ {
+ /* todo: check if smil, if so follow to find uri */
+ sscanf(cur_line,"set the filename of player \"player1\" to \"%s\"",cur_media->uri);
+ cur_media->uri[strlen(cur_media->uri)-1] = '\0'; /* workaround extra character */
+ }
+ else if(!strncmp(cur_line,"set the label of this stack to \"",32))
+ {
+ getquote(cur_line,cur_media->title);
+ }
+ else if(!strncmp(cur_line,"statusMsg \(\"",12))
+ {
+ getquote(cur_line,cur_media->comment);
+ }
+ }
+ }
+ strcpy(cur_line,""); /* reset cur_line */
+ }
+
+ return media;
+}
+
+int smilurl(char * smilurl, med * cur_media)
+/* Extracts url and other data from remote smil file, storing
+ * the info in the cur_media structure. */
+{
+ return 0;
+}
+
+void getquote(char * input, char * quote)
+/* sets quote from a line of the format:
+ * `something "quote" something' */
+{
+ char * cur_pos;
+ cur_pos = quote;
+
+ /* advance until " character is reached */
+ while(*input != '"' && *input)
+ input++;
+
+ input++;
+
+ /* copy characters in until next '"' */
+ while(*input != '"' && *input)
+ {
+ *cur_pos = *input;
+ cur_pos++;
+ input++;
+ }
+
+ *cur_pos = '\0';
+}
+
+void removeleadingspace(char * cur_line)
+{
+ int tmp, newpos;
+
+ char temp_str[STR_MAX];
+
+ /* advance past whitespace */
+ tmp = 0;
+ while (cur_line[tmp] == ' ' || cur_line[tmp] == '\t')
+ tmp++;
+
+ /* copy from there to temp_str */
+ for(newpos = 0; cur_line[tmp]; tmp++, newpos++)
+ temp_str[newpos] = cur_line[tmp];
+
+ temp_str[newpos] = '\0';
+
+ /* copy temp_str to cur_line */
+ strncpy(cur_line, temp_str, sizeof(temp_str));
+}
diff --git a/src/mediaxml.c b/src/mediaxml.c
new file mode 100644
index 0000000..bcb2da1
--- /dev/null
+++ b/src/mediaxml.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <libxml/xmlmemory.h>
+#include <libxml/parser.h>
+
+#include "getht.h"
+#include "issue.h"
+
+int media_accounted_for(char * filepath, issdates * date)
+/* checks if media for issue is found */
+{
+ xmlDocPtr media_file;
+ xmlNodePtr node;
+
+ if(ready_xml(filepath, "media", &media_file, &node))
+ return 1;
+
+ *node = *node->xmlChildrenNode;
+
+ issdates curdate;
+ int found = 1;
+
+ while (node != NULL)
+ {
+ if(!xmlStrcmp(node->name,(char *) "issue"))
+ {
+ curdate.year = atoi( (char *) xmlGetProp(node, "year"));
+ curdate.firstmonth = atoi( (char *) xmlGetProp(node, "firstmonth"));
+ curdate.lastmonth = atoi( (char *) xmlGetProp(node, "lastmonth"));
+ }
+
+ if( curdate.year == date->year &&
+ curdate.firstmonth == date->firstmonth &&
+ curdate.lastmonth == date->lastmonth )
+ {
+ found = 0;
+ break;
+ }
+
+ node = node->next;
+ }
+
+ xmlFreeDoc(media_file);
+
+ return found;
+}
+
+int addmediaissue(char * filepath, char * title, issdates * date, med ** media, int med_no)
+/* Appends data from media structures to xml file. */
+{
+ xmlDocPtr media_file;
+ xmlNodePtr node;
+
+ /* if xml file doesn't exist */
+ if(ready_xml(filepath, "media", &media_file, &node))
+ {
+ /* set up fresh xml file */
+ media_file = xmlNewDoc(NULL);
+ node = xmlNewNode(NULL, "media");
+ xmlDocSetRootElement(media_file, node);
+ }
+
+ xmlNodePtr curissue;
+ char tmp[5];
+
+ /* set up issue node */
+ curissue = xmlNewTextChild(node, NULL, "issue", NULL);
+
+ xmlNewProp(curissue, "title", title);
+
+ snprintf(tmp,5,"%i", date->year);
+ xmlNewProp(curissue, "year", tmp);
+
+ snprintf(tmp,5,"%i",date->firstmonth);
+ xmlNewProp(curissue, "firstmonth", tmp);
+
+ snprintf(tmp,5,"%i",date->lastmonth);
+ xmlNewProp(curissue, "lastmonth", tmp);
+
+ xmlNodePtr curitem;
+
+ int count;
+ for(count = 0; count <= med_no; count++)
+ {
+ curitem = xmlNewTextChild(curissue, NULL, "item", media[count]->title);
+
+ xmlNewProp(curitem, "uri", media[count]->uri);
+
+ if(media[count]->comment)
+ xmlNewProp(curitem, "comment", media[count]->comment);
+ if(media[count]->preview_uri)
+ xmlNewProp(curitem, "preview_uri", media[count]->preview_uri);
+ }
+
+ xmlKeepBlanksDefault(0);
+
+ xmlSaveFormatFile(filepath, media_file, 1);
+
+ xmlFreeDoc(media_file);
+
+ return 0;
+}
+
+iss ** parsemedia(char * filepath, iss ** issue, int * no_of_issues)
+/* Fills issues with relevant info from media xml, creating new
+ ones where necessary. */
+{
+ issdates tmpdate;
+
+ iss * cur_issue; med * cur_media;
+
+ xmlDocPtr media_file;
+ xmlNodePtr node, itnode;
+
+ if(ready_xml(filepath, "media", &media_file, &node))
+ return NULL;
+
+ *node = *node->xmlChildrenNode;
+
+ int issue_there = 0;
+
+ char title[STR_MAX];
+ issdates curdate;
+ int tmp;
+
+ while (node != NULL)
+ {
+ if(!xmlStrcmp(node->name,(char *) "issue"))
+ {
+ /* check if issue with title already exists */
+ for(tmp = 0; tmp < *no_of_issues; tmp++)
+ {
+ curdate.year = atoi( (char *) xmlGetProp(node, "year"));
+ curdate.firstmonth = atoi( (char *) xmlGetProp(node, "firstmonth"));
+ curdate.lastmonth = atoi( (char *) xmlGetProp(node, "lastmonth"));
+
+ if( curdate.year == issue[tmp]->date.year &&
+ curdate.firstmonth == issue[tmp]->date.firstmonth &&
+ curdate.lastmonth == issue[tmp]->date.lastmonth )
+ {
+ issue_there = 1;
+ break;
+ }
+ }
+
+ if(!issue_there)
+ { /* advance to the next free issue */
+ iss ** tmpiss = NULL;
+ if(*no_of_issues == -1)
+ { /* make issue** a new array of issue pointers */
+ if( (tmpiss = malloc(sizeof(iss *))) == NULL )
+ nogo_mem();
+ }
+ else
+ { /* add a new pointer to issue pointer list */
+ if( (tmpiss = realloc(issue, sizeof(iss *) + (*no_of_issues * sizeof(iss *)))) == NULL )
+ nogo_mem();
+ }
+
+ (*no_of_issues)++;
+
+ /* make new array item a pointer to issue */
+ if( (tmpiss[*no_of_issues] = malloc(sizeof(iss))) == NULL )
+ nogo_mem();
+
+ issue = tmpiss;
+
+ issue[*no_of_issues]->date.year = atoi( (char *) xmlGetProp(node, "year"));
+ issue[*no_of_issues]->date.firstmonth = atoi( (char *) xmlGetProp(node, "firstmonth"));
+ issue[*no_of_issues]->date.lastmonth = atoi( (char *) xmlGetProp(node, "lastmonth"));
+
+ strncpy(issue[*no_of_issues]->title, (char *) xmlGetProp(node, "title"), STR_MAX);
+
+ tmp = *no_of_issues;
+ }
+
+ iss * cur_issue = issue[tmp];
+
+ issue[tmp]->no_of_media = -1;
+
+ itnode = node->xmlChildrenNode;
+
+ while (itnode != NULL)
+ {
+
+ if(!xmlStrcmp(itnode->name,(char *) "item"))
+ {
+ /* assign memory for the new media */
+ cur_issue->media = assignnew_med(cur_issue->media, &(cur_issue->no_of_media));
+
+ /* setup media globals */
+ cur_media = cur_issue->media[cur_issue->no_of_media];
+
+ cur_media->uri[0] = '\0';
+ cur_media->title[0] = '\0';
+ cur_media->comment[0] = '\0';
+ cur_media->preview_uri[0] = '\0';
+ cur_media->size = 0;
+
+ /* add media info to cur_media */
+ if(xmlGetProp(itnode, "uri"))
+ strncpy(cur_media->uri, (char *) xmlGetProp(itnode, "uri"), STR_MAX);
+
+ if(xmlGetProp(itnode, "comment"))
+ strncpy(cur_media->comment, (char *) xmlGetProp(itnode, "comment"), STR_MAX);
+
+ if(xmlGetProp(itnode, "preview"))
+ strncpy(cur_media->preview_uri, (char *) xmlGetProp(itnode, "preview_uri"), STR_MAX);
+
+ strncpy(cur_media->title, (char *) xmlNodeListGetString(media_file, itnode->xmlChildrenNode, 1), STR_MAX);
+ }
+
+ itnode = itnode->next;
+ }
+ }
+
+ node = node->next;
+ }
+
+ xmlFreeDoc(media_file);
+
+ issuesort(issue, no_of_issues);
+
+ return issue;
+}
diff --git a/src/tocxml.c b/src/tocxml.c
new file mode 100644
index 0000000..3740326
--- /dev/null
+++ b/src/tocxml.c
@@ -0,0 +1,264 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <libxml/xmlmemory.h>
+#include <libxml/parser.h>
+
+#include "issue.h"
+#include "getht.h"
+
+iss ** parsetoc(char *filepath, int * iss_no, int * latest);
+int parseissue(xmlDocPtr file, xmlNodePtr node, iss * cur_issue, int * latest);
+void parsesection(xmlDocPtr file, xmlNodePtr node, sec * cur_section);
+
+void tokenise_hyphons(char to_token[10], int * first, int * last);
+
+int no_of_issues;
+
+iss ** parsetoc(char *filepath, int * iss_no, int * latest)
+/* starts parsing of xml to issue structure */
+{
+ xmlDocPtr file;
+ xmlNodePtr node;
+
+ if(ready_xml(filepath, "issues", &file, &node))
+ return NULL;
+
+ *node = *node->xmlChildrenNode;
+
+ no_of_issues = -1;
+
+ iss ** issue = NULL;
+
+ int year;
+
+ xmlNodePtr cnode;
+
+ while(node != NULL)
+ {
+ if(!xmlStrncmp(node->name,(char *) "year",4))
+ {
+ cnode = node->children;
+ while(cnode != NULL)
+ {
+ if(!xmlStrncmp(cnode->name,(char *) "issue",5))
+ {
+ /* assign memory for the new issue */
+ issue = assignnew_iss(issue, &no_of_issues);
+
+ /* setup issue globals */
+ issue[no_of_issues]->no_of_media = -1;
+ issue[no_of_issues]->no_of_sections = -1;
+ issue[no_of_issues]->date.year =
+ atoi( (const char *)(xmlStrsub(node->name,5,4)) );
+ tokenise_hyphons(
+ xmlStrsub(cnode->name,6,5),
+ &(issue[no_of_issues]->date.firstmonth),
+ &(issue[no_of_issues]->date.lastmonth));
+
+ /* parse the issue */
+ parseissue(file, cnode, issue[no_of_issues], latest);
+ }
+ cnode = cnode->next;
+ }
+ }
+ node = node->next;
+ }
+
+ xmlFreeDoc(file);
+
+ *iss_no = no_of_issues;
+
+ issuesort(issue, no_of_issues);
+
+ return issue;
+}
+
+int parseissue(xmlDocPtr file, xmlNodePtr node, iss * cur_issue, int * latest)
+/* parses issue from xml, saving in cur_issue structure */
+{
+ strncpy(cur_issue->title, (char *) xmlGetProp(node, "title"), STR_MAX);
+ strncpy(cur_issue->preview_uri, (char *) xmlGetProp(node, "coverlink"), STR_MAX);
+
+ if(xmlGetProp(node, "current") && *latest==-1)
+ *latest = no_of_issues;
+
+ node = node->xmlChildrenNode;
+
+ while(node != NULL){
+ if(!xmlStrncmp(node->name, (char *) "section",7) ||
+ !xmlStrcmp(node->name, (const xmlChar *) "cover"))
+ {
+ /* assign memory for new section */
+ cur_issue->section =
+ assignnew_sec(cur_issue->section, &(cur_issue->no_of_sections));
+
+ /* setup section globals */
+ cur_issue->section[cur_issue->no_of_sections]->no_of_items = -1;
+
+ /* parse the section */
+ parsesection(file, node, cur_issue->section[cur_issue->no_of_sections]);
+ }
+ node = node->next;
+ }
+
+ return 0;
+}
+
+void parsesection(xmlDocPtr file, xmlNodePtr node, sec * cur_section)
+/* parses section xml, filling cur_section structure */
+{
+ it * cur_item = NULL;
+
+ strncpy(cur_section->uri, (char *) xmlGetProp(node, "pdflink"), STR_MAX);
+ strncpy(cur_section->title, (char *) xmlGetProp(node, "title"), STR_MAX);
+
+ if(!xmlStrcmp(node->name, (const xmlChar *) "cover"))
+ cur_section->number = 0;
+ else
+ cur_section->number = atoi( (const char *)(xmlStrsub(node->name,8,1)) );
+
+ node = node->xmlChildrenNode;
+
+ char * pagenums;
+
+ it ** tmp = NULL;
+
+ while(node != NULL)
+ {
+ if(!xmlStrcmp(node->name, (const xmlChar *) "item"))
+ {
+ if(xmlNodeListGetString(file, node->xmlChildrenNode, 1) != NULL)
+ /* ignore items without titles */
+ {
+ /* assign memory for new item */
+ cur_section->item =
+ assignnew_it( cur_section->item, &(cur_section->no_of_items));
+
+ cur_item = cur_section->item[cur_section->no_of_items];
+
+ /* parse item */
+ cur_item->title = xmlNodeListGetString(file, node->xmlChildrenNode, 1);
+ if(pagenums = (char *) xmlGetProp(node, "pages"))
+ tokenise_hyphons(pagenums, &(cur_item->firstpage), &(cur_item->lastpage));
+ else
+ {
+ cur_item->firstpage = 0;
+ cur_item->lastpage = 0;
+ }
+ }
+ }
+ node = node->next;
+ }
+}
+
+void tokenise_hyphons(char to_token[10], int * first, int * last)
+/* splits string to_token, filling positions passed */
+{
+ char token[10];
+ char * tmp;
+
+ tmp = token;
+
+ while(*to_token != '-' && *to_token)
+ {
+ *tmp = *to_token;
+ to_token++; tmp++;
+ }
+
+ *first = atoi(token);
+
+ if(!*to_token)
+ *last = *first;
+ else
+ {
+ to_token++; /* advance past '-' */
+ tmp = token; /* reset tmp */
+ while(*to_token)
+ {
+ *tmp = *to_token;
+ tmp++; to_token++;
+ }
+ *last = atoi(token);
+ }
+}
+
+int cur_identifiers(char * filepath, char * title, issdates * date)
+/* parses xml file to ascertain current issue title and date */
+{
+ xmlDocPtr file;
+
+ if((file = xmlParseFile(filepath)) == NULL)
+ {
+ return 1;
+ }
+
+ xmlNodePtr node,cnode;
+
+ node = xmlDocGetRootElement(file);
+
+ if(node == NULL)
+ {
+ fprintf(stderr,"Error: xml file %s has no root element",filepath);
+ xmlFreeDoc(file);
+ return 1;
+ }
+
+ if(xmlStrcmp(node->name, (const xmlChar *) "issues"))
+ {
+ fprintf(stderr,"Document of the wrong type, root node is '%s' (expected 'issues').\n",(char *) node->name);
+ fprintf(stderr,"Continuing regardless...\n");
+ }
+
+ /* Now that's all sorted, let's do some work */
+
+ node = node->xmlChildrenNode;
+
+ xmlChar *temp;
+ while(node != NULL)
+ {
+ if(!xmlStrncmp(node->name,(char *) "year",4))
+ {
+ cnode = node->children;
+ while(cnode != NULL)
+ {
+ if(!xmlStrncmp(cnode->name,(char *) "issue",5))
+ {
+ temp = xmlGetProp(cnode, "current");
+ if(temp)
+ {
+ strncpy(title, (char *) xmlGetProp(cnode, "title"), STR_MAX);
+ date->year = atoi( (const char *)(xmlStrsub(node->name,5,4)) );
+ tokenise_hyphons(xmlStrsub(cnode->name,6,5), &(date->firstmonth), &(date->lastmonth));
+ return 0;
+ }
+ }
+ cnode = cnode->next;
+ }
+ }
+ node = node->next;
+ }
+
+ return 0;
+}
diff --git a/src/version.h b/src/version.h
new file mode 100644
index 0000000..0713569
--- /dev/null
+++ b/src/version.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#define VERSION "0.0.1"
diff --git a/src/xml.c b/src/xml.c
new file mode 100644
index 0000000..1a3ea3c
--- /dev/null
+++ b/src/xml.c
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2006 Nick White
+ *
+ * This file is part of GetHT
+ *
+ * GetHT 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.
+ *
+ * GetHT 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 GetHT; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <libxml/xmlmemory.h>
+#include <libxml/parser.h>
+
+#include "getht.h"
+#include "issue.h"
+
+int ready_xml(char * filepath, char * rootnode, xmlDocPtr * file, xmlNodePtr * node)
+/* Opens filepath, filling nec pointers with essential information. */
+{
+ if(access(filepath, R_OK) != 0)
+ return 1;
+
+ if((*file = xmlParseFile(filepath)) == NULL)
+ {
+ fprintf(stderr, "Error: cannot open xml file %s\n", filepath);
+ return 1;
+ }
+
+ *node = xmlDocGetRootElement(*file);
+
+ if(*node == NULL)
+ {
+ fprintf(stderr,"Error: xml file %s has no root element",filepath);
+ xmlFreeDoc(*file);
+ return 1;
+ }
+
+ char * test;
+ test = (char *) (*node)->name;
+
+ if(xmlStrcmp((*node)->name, (const xmlChar *) rootnode))
+ {
+ fprintf(stderr,"Document of the wrong type, root node is '%s' (expected '%s').\n",(char *) (*node)->name, rootnode);
+ fprintf(stderr,"Continuing regardless...\n");
+ }
+
+ return 0;
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-31 21:58:43 +0000