Add QPDFObjectHandle::parseContentStream method

This method allows parsing of the PDF objects in a content stream or
array of content streams.

5 files changed, 127 insertions, 1 deletions

diff --git a/examples/build.mk b/examples/build.mk
index 12734b1b..bcb4440e 100644
--- a/examples/build.mk
+++ b/examples/build.mk
@@ -4,7 +4,8 @@ BINS_examples = \
 	pdf-npages \
 	pdf-double-page-size \
 	pdf-invert-images \
-	pdf-create
+	pdf-create \
+	pdf-parse-content
 CBINS_examples = pdf-linearize
 
 TARGETS_examples = $(foreach B,$(BINS_examples) $(CBINS_examples),examples/$(OUTPUT_DIR)/$(call binname,$(B)))
diff --git a/examples/pdf-parse-content.cc b/examples/pdf-parse-content.cc
new file mode 100644
index 00000000..1c3cae16
--- /dev/null
+++ b/examples/pdf-parse-content.cc
@@ -0,0 +1,97 @@
+#include <iostream>
+#include <string.h>
+#include <stdlib.h>
+
+#include <qpdf/QPDF.hh>
+#include <qpdf/QUtil.hh>
+
+static char const* whoami = 0;
+
+void usage()
+{
+    std::cerr << "Usage: " << whoami << " filename page-number" << std::endl
+	      << "Prints a dump of the objects in the content streams"
+              << " of the given page." << std::endl
+              << "Pages are numbered from 1." << std::endl;
+    exit(2);
+}
+
+class ParserCallbacks: public QPDFObjectHandle::ParserCallbacks
+{
+  public:
+    virtual ~ParserCallbacks()
+    {
+    }
+
+    virtual void handleObject(QPDFObjectHandle);
+    virtual void handleEOF();
+};
+
+void
+ParserCallbacks::handleObject(QPDFObjectHandle obj)
+{
+    if (obj.isInlineImage())
+    {
+        std::string val = obj.getInlineImageValue();
+        std::cout << "inline image: ";
+        char buf[3];
+        buf[2] = '\0';
+        for (size_t i = 0; i < val.length(); ++i)
+        {
+            sprintf(buf, "%02x", (unsigned char)(val[i]));
+            std::cout << buf;
+        }
+        std::cout << std::endl;
+    }
+    else
+    {
+        std::cout << obj.unparse() << std::endl;
+    }
+}
+
+void
+ParserCallbacks::handleEOF()
+{
+    std::cout << "-EOF-" << std::endl;
+}
+
+int main(int argc, char* argv[])
+{
+    whoami = QUtil::getWhoami(argv[0]);
+
+    // For libtool's sake....
+    if (strncmp(whoami, "lt-", 3) == 0)
+    {
+	whoami += 3;
+    }
+
+    if (argc != 3)
+    {
+	usage();
+    }
+    char const* filename = argv[1];
+    int pageno = atoi(argv[2]);
+
+    try
+    {
+	QPDF pdf;
+	pdf.processFile(filename);
+        std::vector<QPDFObjectHandle> pages = pdf.getAllPages();
+        if ((pageno < 1) || (pageno > (int)pages.size()))
+        {
+            usage();
+        }
+
+        QPDFObjectHandle page = pages[pageno-1];
+        QPDFObjectHandle contents = page.getKey("/Contents");
+        ParserCallbacks cb;
+        QPDFObjectHandle::parseContentStream(contents, &cb);
+    }
+    catch (std::exception& e)
+    {
+	std::cerr << whoami << ": " << e.what() << std::endl;
+	exit(2);
+    }
+
+    return 0;
+}
diff --git a/examples/qtest/parse-content.test b/examples/qtest/parse-content.test
new file mode 100644
index 00000000..a73566f8
--- /dev/null
+++ b/examples/qtest/parse-content.test
@@ -0,0 +1,17 @@
+#!/usr/bin/env perl
+require 5.008;
+BEGIN { $^W = 1; }
+use strict;
+
+chdir("parse-content");
+
+require TestDriver;
+
+my $td = new TestDriver('pdf-parse-content');
+
+$td->runtest("parse content",
+	     {$td->COMMAND => "pdf-parse-content input.pdf 1"},
+	     {$td->FILE => "content.out", $td->EXIT_STATUS => 0},
+	     $td->NORMALIZE_NEWLINES);
+
+$td->report(1);
diff --git a/examples/qtest/parse-content/content.out b/examples/qtest/parse-content/content.out
new file mode 100644
index 00000000..9c07edc2
--- /dev/null
+++ b/examples/qtest/parse-content/content.out
@@ -0,0 +1,11 @@
+BT
+/F1
+24
+Tf
+72
+720
+Td
+(Potato)
+Tj
+ET
+-EOF-
diff --git a/examples/qtest/parse-content/input.pdf b/examples/qtest/parse-content/input.pdf
new file mode 100644
index 00000000..cd319591
--- /dev/null
+++ b/examples/qtest/parse-content/input.pdf