Add HTTP support using libcurl

With libcurl, poppler can handle documents over http.

9 files changed, 219 insertions, 1 deletions

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 7922dadf..70b0e06d 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -29,6 +29,7 @@ option(ENABLE_CPP "Compile poppler cpp wrapper." ON)
 option(ENABLE_ABIWORD "Build the Abiword backend." ON)
 option(ENABLE_LIBOPENJPEG "Use libopenjpeg for JPX streams." ON)
 option(ENABLE_LCMS "Use liblcms for color management." ON)
+option(ENABLE_LIBCURL "Build libcurl based HTTP support." OFF)
 option(ENABLE_ZLIB "Build with zlib (not totally safe)." OFF)
 option(USE_EXCEPTIONS "Throw exceptions to deal with not enough memory and similar problems." OFF)
 option(USE_FIXEDPOINT "Use fixed point arithmetic in the Splash backend" OFF)
@@ -132,6 +133,11 @@ if(ENABLE_LCMS)
   find_package(LCMS)
   set(USE_CMS ${LCMS_FOUND})
 endif(ENABLE_LCMS)
+if(ENABLE_LIBCURL)
+  find_package(CURL)
+  include_directories(${CURL_INCLUDE_DIR})
+  set(POPPLER_HAS_CURL_SUPPORT ON)
+endif(ENABLE_LIBCURL)
 
 add_definitions(-DHAVE_CONFIG_H=1)
 if(FONTCONFIG_FOUND)
@@ -311,6 +317,12 @@ if(ENABLE_ZLIB)
   )
   set(poppler_LIBS ${poppler_LIBS} ${ZLIB_LIBRARIES})
 endif(ENABLE_ZLIB)
+if(ENABLE_LIBCURL)
+  set(poppler_SRCS ${poppler_SRCS}
+    poppler/CurlCachedFile.cc
+  )
+  set(poppler_LIBS ${poppler_LIBS} ${CURL_LIBRARIES})
+endif(ENABLE_LIBCURL)
 if(LIBOPENJPEG_FOUND)
   set(poppler_SRCS ${poppler_SRCS}
     poppler/JPEG2000Stream.cc
@@ -442,6 +454,11 @@ if(ENABLE_XPDF_HEADERS)
     fofi/FoFiType1.h
     fofi/FoFiType1C.h
     DESTINATION include/poppler/fofi)
+  if(ENABLE_LIBCURL)
+    install(FILES
+      poppler/CurlCachedFile.h
+      DESTINATION include/poppler)
+  endif(ENABLE_LIBCURL)
   if(LIBOPENJPEG_FOUND)
     install(FILES
       poppler/JPEG2000Stream.h
@@ -552,6 +569,7 @@ show_end_message("use gtk-doc" "not supported with this CMake build system")
 show_end_message_yesno("use libjpeg" ENABLE_LIBJPEG)
 show_end_message_yesno("use libpng" ENABLE_LIBPNG)
 show_end_message_yesno("use zlib" ENABLE_ZLIB)
+show_end_message_yesno("use curl" ENABLE_LIBCURL)
 show_end_message_yesno("use libopenjpeg" LIBOPENJPEG_FOUND)
 show_end_message_yesno("use cms" USE_CMS)
 show_end_message_yesno("command line utils" ENABLE_UTILS)
diff --git a/config.h.cmake b/config.h.cmake
index 70d8d5d2..0879aeb5 100644
--- a/config.h.cmake
+++ b/config.h.cmake
@@ -1,5 +1,8 @@
 /* config.h.  Generated from config.h.cmake by cmake.  */
 
+/* Build against libcurl. */
+#cmakedefine ENABLE_LIBCURL 1
+
 /* Use libjpeg instead of builtin jpeg decoder. */
 #cmakedefine ENABLE_LIBJPEG 1
 
@@ -153,6 +156,9 @@
 /* Poppler data dir */
 #define POPPLER_DATADIR "${CMAKE_INSTALL_PREFIX}/share/poppler"
 
+/* Support for curl based doc builder is compiled in. */
+#cmakedefine POPPLER_HAS_CURL_SUPPORT 1
+
 /* Have GDK */
 #cmakedefine POPPLER_WITH_GDK 1
 
diff --git a/configure.ac b/configure.ac
index 68509eee..72041d51 100644
--- a/configure.ac
+++ b/configure.ac
@@ -210,6 +210,21 @@ AM_CONDITIONAL(BUILD_ZLIB, test x$enable_zlib = xyes)
 AH_TEMPLATE([ENABLE_ZLIB],
 	    [Use zlib instead of builtin zlib decoder.])
 
+dnl Test for libcurl
+AC_ARG_ENABLE(libcurl,
+	      AC_HELP_STRING([--enable-libcurl],
+	                     [Build with libcurl based HTTP support.]),
+              enable_libcurl=$enableval,
+              enable_libcurl="no")
+
+if test x$enable_libcurl = xyes; then
+  PKG_CHECK_MODULES(LIBCURL, libcurl)
+  AC_DEFINE(ENABLE_LIBCURL, 1, [Build against libcurl.])
+  AC_DEFINE(POPPLER_HAS_CURL_SUPPORT, 1,
+     [Support for curl based doc builder is compiled in.])
+fi
+
+AM_CONDITIONAL(BUILD_LIBCURL, test x$enable_libcurl = xyes)
 
 dnl Test for libjpeg
 AC_ARG_ENABLE(libjpeg,
@@ -651,6 +666,7 @@ echo "  use gtk-doc:        $enable_gtk_doc"
 echo "  use libjpeg:        $enable_libjpeg"
 echo "  use libpng:         $enable_libpng"
 echo "  use zlib:           $enable_zlib"
+echo "  use libcurl:        $enable_libcurl"
 echo "  use libopenjpeg:    $enable_libopenjpeg"
 echo "  use cms:            $enable_cms"
 echo "  command line utils: $enable_utils"
diff --git a/poppler/CurlCachedFile.cc b/poppler/CurlCachedFile.cc
new file mode 100644
index 00000000..b326fb7d
--- /dev/null
+++ b/poppler/CurlCachedFile.cc
@@ -0,0 +1,95 @@
+//========================================================================
+//
+// CurlCachedFile.cc
+//
+// This file is licensed under the GPLv2 or later
+//
+// Copyright 2009 Stefan Thomas <thomas@eload24.com>
+// Copyright 2010 Hib Eris <hib@hiberis.nl>
+//
+//========================================================================
+
+#include <config.h>
+
+#include "CurlCachedFile.h"
+
+#include "goo/GooString.h"
+#include "goo/GooVector.h"
+
+//------------------------------------------------------------------------
+
+CurlCachedFileLoader::CurlCachedFileLoader()
+{
+  url = NULL;
+  cachedFile = NULL;
+  curl = NULL;
+}
+
+CurlCachedFileLoader::~CurlCachedFileLoader() {
+  curl_easy_cleanup(curl);
+}
+
+static size_t
+noop_cb(char *ptr, size_t size, size_t nmemb, void *ptr2)
+{
+  return size*nmemb;
+}
+
+size_t
+CurlCachedFileLoader::init(GooString *urlA, CachedFile *cachedFileA)
+{
+  long code = NULL;
+  double contentLength = -1;
+  size_t size;
+
+  url = urlA;
+  cachedFile = cachedFileA;
+  curl = curl_easy_init();
+
+  curl_easy_setopt(curl, CURLOPT_URL, url->getCString());
+  curl_easy_setopt(curl, CURLOPT_HEADER, 1);
+  curl_easy_setopt(curl, CURLOPT_NOBODY, 1);
+  curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, &noop_cb);
+  curl_easy_perform(curl);
+  curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &code);
+  curl_easy_getinfo(curl, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &contentLength);
+  curl_easy_reset(curl);
+
+  size = contentLength;
+
+  return size;
+}
+
+static
+size_t load_cb(const char *ptr, size_t size, size_t nmemb, void *data)
+{
+  CachedFileWriter *writer = (CachedFileWriter *) data;
+  return (writer->write) (ptr, size*nmemb);
+}
+
+int CurlCachedFileLoader::load(GooVector<ByteRange> *ranges, CachedFileWriter *writer)
+{
+  CURLcode r = CURLE_OK;
+  size_t fromByte, toByte;
+  for (size_t i = 0; i < (*ranges).size(); i++) {
+
+     fromByte = (*ranges)[i].offset;
+     toByte = fromByte + (*ranges)[i].length - 1;
+     GooString *range = GooString::format("{0:ud}-{1:ud}", fromByte, toByte);
+
+     curl_easy_setopt(curl, CURLOPT_URL, url->getCString());
+     curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, load_cb);
+     curl_easy_setopt(curl, CURLOPT_WRITEDATA, writer);
+     curl_easy_setopt(curl, CURLOPT_RANGE, range->getCString());
+     r = curl_easy_perform(curl);
+     curl_easy_reset(curl);
+
+     delete range;
+
+     if (r != CURLE_OK) break;
+  }
+  return r;
+}
+
+//------------------------------------------------------------------------
+
diff --git a/poppler/CurlCachedFile.h b/poppler/CurlCachedFile.h
new file mode 100644
index 00000000..b18b7f86
--- /dev/null
+++ b/poppler/CurlCachedFile.h
@@ -0,0 +1,39 @@
+//========================================================================
+//
+// CurlCachedFile.h
+//
+// This file is licensed under the GPLv2 or later
+//
+// Copyright 2010 Hib Eris <hib@hiberis.nl>
+//
+//========================================================================
+
+#ifndef CURLCACHELOADER_H
+#define CURLCACHELOADER_H
+
+#include "poppler-config.h"
+#include "CachedFile.h"
+
+#include <curl/curl.h>
+
+//------------------------------------------------------------------------
+
+class CurlCachedFileLoader : public CachedFileLoader {
+
+public:
+
+  CurlCachedFileLoader();
+  ~CurlCachedFileLoader();
+  size_t init(GooString *url, CachedFile* cachedFile);
+  int load(GooVector<ByteRange> *ranges, CachedFileWriter *writer);
+
+private:
+
+  GooString *url;
+  CachedFile *cachedFile;
+  CURL *curl;
+
+};
+
+#endif
+
diff --git a/poppler/Makefile.am b/poppler/Makefile.am
index a6bb9e97..5cd68a41 100644
--- a/poppler/Makefile.am
+++ b/poppler/Makefile.am
@@ -102,6 +102,22 @@ zlib_libs = 					\
 
 endif
 
+if BUILD_LIBCURL
+
+libcurl_libs =					\
+	$(LIBCURL_LIBS)
+
+libcurl_includes =				\
+	$(LIBCURL_CFLAGS)
+
+curl_headers =					\
+	CurlCachedFile.h
+
+curl_sources =					\
+	CurlCachedFile.cc
+
+endif
+
 if BUILD_ABIWORD_OUTPUT
 
 abiword_sources =				\
@@ -130,6 +146,7 @@ INCLUDES =					\
 	$(arthur_includes)			\
 	$(abiword_includes)			\
 	$(libpng_includes)			\
+	$(libcurl_includes)			\
 	$(FREETYPE_CFLAGS)			\
 	$(FONTCONFIG_CFLAGS)
 
@@ -149,6 +166,7 @@ libpoppler_la_LIBADD =				\
 	$(libjpeg_libs)				\
 	$(libpng_libs)				\
 	$(zlib_libs)				\
+	$(libcurl_libs)				\
 	$(libjpeg2000_libs)			\
 	$(abiword_libs)				\
 	$(FREETYPE_LIBS)			\
@@ -163,6 +181,7 @@ if ENABLE_XPDF_HEADERS
 poppler_includedir = $(includedir)/poppler
 poppler_include_HEADERS =	\
 	$(splash_headers)	\
+	$(curl_headers)		\
 	Annot.h			\
 	Array.h			\
 	BuiltinFont.h		\
@@ -237,6 +256,7 @@ libpoppler_la_SOURCES =		\
 	$(zlib_sources)		\
 	$(libjpeg2000_sources)	\
 	$(abiword_sources)	\
+	$(curl_sources)		\
 	Annot.cc		\
 	Array.cc 		\
 	BuiltinFont.cc		\
diff --git a/poppler/poppler-config.h.cmake b/poppler/poppler-config.h.cmake
index 7656e4f0..95e95ccd 100644
--- a/poppler/poppler-config.h.cmake
+++ b/poppler/poppler-config.h.cmake
@@ -49,6 +49,11 @@
 #cmakedefine WITH_FONTCONFIGURATION_WIN32 1
 #endif
 
+/* Support for curl is compiled in. */
+#ifndef POPPLER_HAS_CURL_SUPPORT
+#cmakedefine POPPLER_HAS_CURL_SUPPORT 1
+#endif
+
 // Also, there's a couple of preprocessor symbols in the header files
 // that are used but never defined: DISABLE_OUTLINE, DEBUG_MEM and
 
diff --git a/poppler/poppler-config.h.in b/poppler/poppler-config.h.in
index f8db4ba4..7b0644c6 100644
--- a/poppler/poppler-config.h.in
+++ b/poppler/poppler-config.h.in
@@ -49,6 +49,11 @@
 #undef WITH_FONTCONFIGURATION_WIN32
 #endif
 
+/* Support for curl is compiled in. */
+#ifndef POPPLER_HAS_CURL_SUPPORT
+#undef POPPLER_HAS_CURL_SUPPORT
+#endif
+
 // Also, there's a couple of preprocessor symbols in the header files
 // that are used but never defined: DISABLE_OUTLINE, DEBUG_MEM and
 
diff --git a/utils/pdfinfo.cc b/utils/pdfinfo.cc
index ceddd47d..48504d2c 100644
--- a/utils/pdfinfo.cc
+++ b/utils/pdfinfo.cc
@@ -49,6 +49,9 @@
 #include "Error.h"
 #include "DateInfo.h"
 #include "StdinCachedFile.h"
+#if ENABLE_LIBCURL
+#include "CurlCachedFile.h"
+#endif
 
 static void printInfoString(Dict *infoDict, char *key, char *text,
 			    UnicodeMap *uMap);
@@ -160,7 +163,18 @@ int main(int argc, char *argv[]) {
     userPW = NULL;
   }
 
-  if(fileName->cmp("-") != 0) {
+#if ENABLE_LIBCURL
+  if (fileName->cmpN("http://", 7) == 0 ||
+           fileName->cmpN("https://", 8) == 0) {
+      Object obj;
+
+      obj.initNull();
+      CachedFile *cachedFile = new CachedFile(new CurlCachedFileLoader(), fileName);
+      doc = new PDFDoc(new CachedFileStream(cachedFile, 0, gFalse, 0, &obj),
+                       ownerPW, userPW);
+  } else
+#endif
+  if (fileName->cmp("-") != 0) {
       doc = new PDFDoc(fileName, ownerPW, userPW);
   } else {
       Object obj;