"
@@ -167,6 +172,7 @@ MainAttachment::addLink (string &plain, string &html, const string &url, const s
plain += plainNewOneLink;
string htmlNewOneLink (templateHtmlAddLink);
string codedUrl (url);
+ // XXX amp ?
replaceAll (codedUrl, "&", "&");
replaceAll (htmlNewOneLink, TMPL_DOWNLOAD, codedUrl);
replaceAll (htmlNewOneLink, TMPL_FILENAME, name);
@@ -218,9 +224,9 @@ MainAttachment::getDisclaim (string &plain, string &html) const {
string allPlainLinks (templatePlainAllLink);
replaceAll (allPlainLinks, TMPL_DOWNLOAD, archiveDownloadURL);
plain += allPlainLinks;
- string allLinks (templateHtmlAllLink);
- replaceAll (allLinks, TMPL_DOWNLOAD, archiveDownloadURL);
- html += allLinks;
+ string allHtmlLinks (templateHtmlAllLink);
+ replaceAll (allHtmlLinks, TMPL_DOWNLOAD, archiveDownloadURL);
+ html += allHtmlLinks;
}
html += templateHtmlFooter;
plain += "\r\n\r\n"+KAZ_WEB_SITE+"\r\n"+KAZ_PLAIN_HR+"\r\n"+KAZ_PLAIN_STOP+"\r\n";
@@ -245,6 +251,7 @@ MainAttachment::addPrevious (const string &href, const string &name, const bool
void
MainAttachment::extractLinks (const string &extractedPlainKAZ) {
+ // plain text => "* name
"
DEF_LOG ("Attachment::extractedPlainKAZ", "extractedPlainKAZ: " << extractedPlainKAZ);
for (string::size_type startPos (0);
(startPos = extractedPlainKAZ.find ("http", startPos)) != string::npos;
@@ -257,22 +264,30 @@ MainAttachment::extractLinks (const string &extractedPlainKAZ) {
if (extractedPlainKAZ [stopPos])
++stopPos;
+ streamoff stopName = startPos;
startPos = stopPos;
+
// get all href but KAZ_WEB_SITE
// the archive link will be skip by filter.sh
if (href == KAZ_WEB_SITE)
continue;
- string::size_type nextPos = extractedPlainKAZ.find ("http", startPos);
- string name (extractedPlainKAZ, startPos, (nextPos == string::npos ? extractedPlainKAZ.length () : nextPos) - startPos);
- // skip [> \r\n\t]
- nextPos = name.find_first_not_of ("[> \t\r\n\"]");
- if (nextPos != string::npos)
- name.erase (0, nextPos);
- // stop before [>\r\n\t]
- nextPos = name.find_first_of ("[\"]");
- if (nextPos != string::npos)
- name.erase (nextPos);
+ // backward find name
+ string::size_type startName = extractedPlainKAZ.rfind ("* ", stopName);
+ string name;
+
+ if (startName != string::npos) {
+ name = string (extractedPlainKAZ, startName+3, stopName - startName - 3);
+ // skip [> \r\n\t]
+ string::size_type nextPos = name.find_first_not_of ("[>< \t\r\n\"]");
+ if (nextPos != string::npos)
+ name.erase (0, nextPos);
+ // stop before [>\r\n\t]
+ nextPos = name.find_first_of ("[\"<]");
+ if (nextPos != string::npos)
+ name.erase (nextPos);
+ }
+
LOG ("plain name: " << name);
addPrevious (href, name);
}
@@ -281,6 +296,7 @@ MainAttachment::extractLinks (const string &extractedPlainKAZ) {
// ================================================================================
void
MainAttachment::extractLinks (const vector &liOne) {
+ // html text => "name"
DEF_LOG ("Attachment::extractedPlainKAZ", "liOne.size: " << liOne.size ());
for (const string &one : liOne) {
if (caseInsensitiveFind (one, CLASS_ONE) == string::npos)
@@ -353,10 +369,11 @@ MainAttachment::extractPreviousKAZ (ifstream &mbox) {
void
MainAttachment::removePreviousArchive () {
vector toRemove;
- for (map ::const_iterator it = previousLinks.begin (); it != previousLinks.end (); ++it)
- if (it->first.find ("&g=") != string::npos ||
- it->first.find ("&l=/") != string::npos) // v1 compatibility
- toRemove.push_back (it->first);
+ for (map ::const_iterator it = previousLinks.begin (); it != previousLinks.end (); ++it) {
+ const string key (it->first);
+ if (regex_match (key, archiveURLSignature))
+ toRemove.push_back (key);
+ }
for (string old : toRemove)
previousLinks.erase (old);
}
@@ -521,8 +538,10 @@ MainAttachment::substitute (ifstream &mbox, ofstream &outbox, const SizeArg &min
continue;
for (EmbeddedData &embedded : attachP->embeddedData)
readDownloadUrl (embedded.downloadUrl);
+ // XXX test empty ?
}
readArchiveUrl ();
+ removePreviousArchive ();
string plainDisclaim, htmlDisclaim;
getDisclaim (plainDisclaim, htmlDisclaim);
// copy email
diff --git a/src/cpp/eMailShrinker.cpp b/src/cpp/eMailShrinker.cpp
index 6eb094a..5340bdd 100644
--- a/src/cpp/eMailShrinker.cpp
+++ b/src/cpp/eMailShrinker.cpp
@@ -32,7 +32,7 @@
// knowledge of the CeCILL-B license and that you accept its terms. //
////////////////////////////////////////////////////////////////////////////
-#define LAST_VERSION "2.0 2022-02-08 eMailShrinker"
+#define LAST_VERSION "2.1 2022-10-30 eMailShrinker"
#include
#include
@@ -188,10 +188,10 @@ main (int argc, char** argv) {
MainAttachment attachment (mbox);
mbox.close ();
- if (attachment.getBoundary ().empty ()) {
- cerr << "no attachment" << endl;
- return 1;
- }
+ // if (attachment.getBoundary ().empty ()) {
+ // cerr << "no attachment" << endl;
+ // return 1;
+ // }
// parse structure
mbox.open (inputName);
attachment.markSignificant (minAttachSize, mbox);
diff --git a/src/cpp/jirafeauAPI.cpp b/src/cpp/jirafeauAPI.cpp
index 17b6470..46b0706 100644
--- a/src/cpp/jirafeauAPI.cpp
+++ b/src/cpp/jirafeauAPI.cpp
@@ -32,7 +32,7 @@
// knowledge of the CeCILL-B license and that you accept its terms. //
////////////////////////////////////////////////////////////////////////////
-#define LAST_VERSION "1.0 2021-02-21 jirafeauAPI"
+#define LAST_VERSION "1.1 2022-10-30 jirafeauAPI"
#include
#include
@@ -281,12 +281,13 @@ main (int argc, char** argv) {
}
curl_easy_setopt (easyhandle, CURLOPT_MIMEPOST, multipart);
- curl_easy_perform (easyhandle);
+ CURLcode res (curl_easy_perform (easyhandle));
curl_easy_cleanup (easyhandle);
cout << readBuffer << endl;
showTime ("Upload");
-
+ if (res != CURLE_OK)
+ cerr << prog << " failed: " << curl_easy_strerror (res) << endl;
return 0;
}
diff --git a/src/include/Attachment.hpp b/src/include/Attachment.hpp
index 0ffef82..62d0e20 100644
--- a/src/include/Attachment.hpp
+++ b/src/include/Attachment.hpp
@@ -35,9 +35,9 @@
#ifndef _kaz_Attachment_hpp
#define _kaz_Attachment_hpp
-#include
-#include
#include