browser_tests now use pre computed html

pdf2htmlEX/test/browser_tests.py

@@ -37,13 +37,23 @@ class BrowserTests(Common):
         ref_htmlfolder = os.path.join(self.TEST_DATA_DIR, basefilename)
         ref_htmlfilename = os.path.join(ref_htmlfolder, htmlfilename)
         out_htmlfilename = os.path.join(self.OUTDIR, htmlfilename)
+        pre_htmlfilename = os.path.join(self.PREDIR, htmlfilename)
         
-        pdf2htmlEX_args = self.DEFAULT_PDF2HTMLEX_ARGS + args + [
+        try:
+            # see if we have pre-compiled the html file...
+            # if so simply copy it into place
+            #
+            shutil.copy(pre_htmlfilename, out_htmlfilename)
+        except:
+            # we have not pre-compiled the html file
+            # so create it using pdf2htmlEX
+            #
+            pdf2htmlEX_args = self.DEFAULT_PDF2HTMLEX_ARGS + args + [
                 os.path.join(self.TEST_DATA_DIR, filename),
                 htmlfilename ]
-        result = self.run_pdf2htmlEX(pdf2htmlEX_args)
-
-        self.assertIn(htmlfilename, result['output_files'], 'HTML file is not generated')
+            result = self.run_pdf2htmlEX(pdf2htmlEX_args)
+            #
+            self.assertIn(htmlfilename, result['output_files'], 'HTML file is not generated')
 
         if self.GENERATING_MODE:
             # copy generated html files

pdf2htmlEX/test/produceHtmlForBrowserTests

@@ -0,0 +1,82 @@
+#!/bin/bash
+
+# This bash script walks through the browser_tests directory running 
+# pdf2htmlEX on each *.pdf file. 
+
+# This is how we run pdf2htmlEX on a particular file, and arguments.
+#
+function runPdf2htmlEX {
+  pdfFileName=$1
+  htmlFileName=$(echo $pdfFileName | cut -d'.' -f1).html
+  arguments=$2
+  #
+  echo ""
+  echo "---"
+  echo " pdfFileName: [$pdfFileName]"
+  echo "htmlFileName: [$htmlFileName]"
+  echo "   arguments: [$arguments]"
+  #  
+  # now run pdf2htmlEX to produce the output files
+  #
+  echo $PDF2HTMLEX_PATH           \
+    --data-dir=$PDF2HTMLEX_DATDIR \
+    --dest-dir $PDF2HTMLEX_TMPDIR \
+    --fit-width=800 --last-page=1 \
+    $arguments                    \
+    browser_tests/$pdfFileName    \
+    $htmlFileName
+  #
+  $PDF2HTMLEX_PATH                \
+    --data-dir=$PDF2HTMLEX_DATDIR \
+    --dest-dir $PDF2HTMLEX_TMPDIR \
+    --fit-width=800 --last-page=1 \
+    $arguments                    \
+    browser_tests/$pdfFileName    \
+    $htmlFileName
+}
+
+if test -z "$PDF2HTMLEX_PATH" ; then 
+  echo "PANIC: we do not know where to find the pdf2htmlEX executable"
+  exit 1
+fi
+
+if test -z "$PDF2HTMLEX_DATDIR" ; then
+  export PDF2HTMLEX_DATDIR=/tmp/pdf2htmlEX/dat
+fi
+
+if test -z "$PDF2HTMLEX_TMPDIR" ; then
+  export PDF2HTMLEX_TMPDIR=/tmp/pdf2htmlEX/tmp
+fi
+
+if test -z "$PDF2HTMLEX_PREDIR" ; then
+  export PDF2HTMLEX_PREDIR=/tmp/pdf2htmlEX/pre
+fi
+
+# clear out the TMPDIR
+#
+rm    -rf $PDF2HTMLEX_TMPDIR
+mkdir -p  $PDF2HTMLEX_TMPDIR
+#
+
+runPdf2htmlEX 'test_fail.pdf'
+
+runPdf2htmlEX 'basic_text.pdf'
+
+runPdf2htmlEX 'geneve_1564.pdf'
+
+runPdf2htmlEX 'text_visibility.pdf' '--correct-text-visibility=1'
+
+runPdf2htmlEX 'with_form.pdf' '--process-form=1'
+
+runPdf2htmlEX 'invalid_unicode_issue477.pdf'
+
+runPdf2htmlEX 'svg_background_with_page_rotation_issue402.pdf' '--bg-format=svg'
+
+runPdf2htmlEX 'fontfile3_opentype.pdf'
+
+# clear out the PREDIR
+#
+rm    -rf $PDF2HTMLEX_PREDIR
+mkdir -p  $PDF2HTMLEX_PREDIR
+#
+cp $PDF2HTMLEX_TMPDIR/* $PDF2HTMLEX_PREDIR

pdf2htmlEX/test/test.py.in

@@ -28,6 +28,7 @@ class Common(object):
     PNGDIR = "@PDF2HTMLEX_PNGDIR@"
     DATDIR = "@PDF2HTMLEX_DATDIR@"
     OUTDIR = "@PDF2HTMLEX_OUTDIR@"
+    PREDIR = "@PDF2HTMLEX_PREDIR@"
     HTMDIR = "@PDF2HTMLEX_HTMDIR@"
 
     def setUp(self):