Implement deterministic ID

For non-encrypted files, determinstic ID generation uses file contents
instead of timestamp and file name. At a small runtime cost, this
enables generation of the same /ID if the same inputs are converted in
the same way multiple times.

1 files changed, 41 insertions, 20 deletions

diff --git a/libqpdf/Pl_MD5.cc b/libqpdf/Pl_MD5.cc
index 3a78cb33..0510e50e 100644
--- a/libqpdf/Pl_MD5.cc
+++ b/libqpdf/Pl_MD5.cc
@@ -3,7 +3,9 @@
 
 Pl_MD5::Pl_MD5(char const* identifier, Pipeline* next) :
     Pipeline(identifier, next),
-    in_progress(false)
+    in_progress(false),
+    enabled(true),
+    persist_across_finish(false)
 {
 }
 
@@ -14,24 +16,27 @@ Pl_MD5::~Pl_MD5()
 void
 Pl_MD5::write(unsigned char* buf, size_t len)
 {
-    if (! this->in_progress)
+    if (this->enabled)
     {
-	this->md5.reset();
-	this->in_progress = true;
-    }
+        if (! this->in_progress)
+        {
+            this->md5.reset();
+            this->in_progress = true;
+        }
 
-    // Write in chunks in case len is too big to fit in an int.
-    // Assume int is at least 32 bits.
-    static size_t const max_bytes = 1 << 30;
-    size_t bytes_left = len;
-    unsigned char* data = buf;
-    while (bytes_left > 0)
-    {
-	size_t bytes = (bytes_left >= max_bytes ? max_bytes : bytes_left);
-        this->md5.encodeDataIncrementally(
-            reinterpret_cast<char*>(data), bytes);
-	bytes_left -= bytes;
-        data += bytes;
+        // Write in chunks in case len is too big to fit in an int.
+        // Assume int is at least 32 bits.
+        static size_t const max_bytes = 1 << 30;
+        size_t bytes_left = len;
+        unsigned char* data = buf;
+        while (bytes_left > 0)
+        {
+            size_t bytes = (bytes_left >= max_bytes ? max_bytes : bytes_left);
+            this->md5.encodeDataIncrementally(
+                reinterpret_cast<char*>(data), bytes);
+            bytes_left -= bytes;
+            data += bytes;
+        }
     }
 
     this->getNext()->write(buf, len);
@@ -41,16 +46,32 @@ void
 Pl_MD5::finish()
 {
     this->getNext()->finish();
-    this->in_progress = false;
+    if (! this->persist_across_finish)
+    {
+        this->in_progress = false;
+    }
+}
+
+void
+Pl_MD5::enable(bool enabled)
+{
+    this->enabled = enabled;
+}
+
+void
+Pl_MD5::persistAcrossFinish(bool persist)
+{
+    this->persist_across_finish = persist;
 }
 
 std::string
 Pl_MD5::getHexDigest()
 {
-    if (this->in_progress)
+    if (! this->enabled)
     {
 	throw std::logic_error(
-	    "digest requested for in-progress MD5 Pipeline");
+	    "digest requested for a disabled MD5 Pipeline");
     }
+    this->in_progress = false;
     return this->md5.unparse();
 }