From 6bcb941bcff5e73b62ecc8d2aa5691d3e0e7afc0 Mon Sep 17 00:00:00 2001
From: Robin Watts <Robin.Watts@artifex.com>
Date: Mon, 27 Apr 2020 15:14:14 +0100
Subject: [PATCH] Avoid tesseract writing Pix out/reading them back.

By default, when we ImageData::SetPix, we write the data out as a
PNG, just to read it back in to get a compressed buffer of data.
We then use this to generate a new Pix.

In builds of Tesseract on systems where we don't have temp files,
writing files out is problematic.

Not only that, but compressing/uncompressing is slow, and on minimal
builds of leptonica, where we've disabled the format writers to reduce
memory footprint, we get no compression anyway.

In such cases, it'd be far nicer just to keep the original Pix as
the internal data.

Also, when recovering the pixmap from the ImageData, if we know we're
only going to read from the data, we can avoid duplicating it and
just use the original. This is exactly the case when GRAPHICS_DISABLED
is set.

So, introduce a TESSERACT_IMAGEDATA_AS_PIX predefine that we can use
to cause the internal data to be a Pix rather than a compressed
buffer.



Given we don't do compression, and they were writing to memory,
this was all just more effort than we needed.

Also, if we're using GRAPHICS_DISABLED, we might as well just
pixCopy rather than pixClone as only the scaler uses this.
---
 src/ccstruct/imagedata.cpp | 18 ++++++++++++++++++
 src/ccstruct/imagedata.h   |  3 +++
 2 files changed, 21 insertions(+)

diff --git a/src/ccstruct/imagedata.cpp b/src/ccstruct/imagedata.cpp
index ad8fcc7b..3328b5e9 100644
--- a/src/ccstruct/imagedata.cpp
+++ b/src/ccstruct/imagedata.cpp
@@ -207,12 +207,28 @@ bool ImageData::SkipDeSerialize(TFile* fp) {
 // In case of missing PNG support in Leptonica use PNM format,
 // which requires more memory.
 void ImageData::SetPix(Pix* pix) {
+#ifdef TESSERACT_IMAGEDATA_AS_PIX
+  internal_pix_ = pix;
+#else
   SetPixInternal(pix, &image_data_);
+#endif
 }
 
 // Returns the Pix image for *this. Must be pixDestroyed after use.
 Pix* ImageData::GetPix() const {
+#ifdef TESSERACT_IMAGEDATA_AS_PIX
+#ifdef GRAPHICS_DISABLED
+  /* The only caller of this is the scaling functions to prescale the
+   * source. Thus we can just return a new pointer to the same data. */
+  return pixClone(internal_pix_);
+#else
+  /* pixCopy always does an actual copy, so the caller can modify the
+   * changed data. */
+  return pixCopy(NULL, internal_pix_);
+#endif
+#else
   return GetPixInternal(image_data_);
+#endif
 }
 
 // Gets anything and everything with a non-nullptr pointer, prescaled to a
@@ -320,6 +336,7 @@ void ImageData::AddBoxes(const GenericVector<TBOX>& boxes,
   }
 }
 
+#ifndef TESSERACT_IMAGEDATA_AS_PIX
 // Saves the given Pix as a PNG-encoded string and destroys it.
 // In case of missing PNG support in Leptonica use PNM format,
 // which requires more memory.
@@ -348,6 +365,7 @@ Pix* ImageData::GetPixInternal(const GenericVector<char>& image_data) {
   }
   return pix;
 }
+#endif
 
 // Parses the text string as a box file and adds any discovered boxes that
 // match the page number. Returns false on error.
diff --git a/src/ccstruct/imagedata.h b/src/ccstruct/imagedata.h
index b5492c71..563e5561 100644
--- a/src/ccstruct/imagedata.h
+++ b/src/ccstruct/imagedata.h
@@ -196,6 +196,9 @@ class ImageData {
  private:
   STRING imagefilename_;             // File to read image from.
   int32_t page_number_;              // Page number if multi-page tif or -1.
+#ifdef TESSERACT_IMAGEDATA_AS_PIX
+  Pix *internal_pix_;
+#endif
   GenericVector<char> image_data_;   // PNG/PNM file data.
   STRING language_;                  // Language code for image.
   STRING transcription_;             // UTF-8 ground truth of image.