Merge pull request #7 from CoreFiling/feature/fix-tab-characters

Map tab characters to spaces rather than private use area

Author: nicolas-duvauchel

CHANGELOG.md

@@ -7,7 +7,7 @@
 * Add optional overrides for command-line arguments passed to `pdf2htmlEX`.
 * Patch and build `pdf2htmlEX` as part of this build process to use `libopenjp` instead of `libjpeg` for JPEG-2000 support.
   * All patches are in this source tree, and are applied to directly to the source of the upstream tag during build.
-* Patch issue with non-breaking spaces in `pdf2HTMLEX`.
+* Patch issue with non-breaking spaces and tab characters in `pdf2HTMLEX`.
 * Convert complex SVGs images to bitmaps.
 
 ## 0.1.0

src/Pdf2Html/Dockerfile

@@ -19,6 +19,7 @@ RUN patch ./buildScripts/versionEnvs ./patches/versionEnvs.patch
 RUN patch ./buildScripts/buildPoppler ./patches/buildPoppler.patch
 RUN patch ./buildScripts/getBuildToolsApt ./patches/getBuildToolsApt.patch
 RUN patch ./buildScripts/getDevLibrariesApt ./patches/getDevLibrariesApt.patch
+RUN patch ./pdf2htmlEX/src/util/unicode.cc ./patches/unicode.cc.patch
 RUN patch ./pdf2htmlEX/src/util/unicode.h ./patches/unicode.h.patch
 RUN patch ./pdf2htmlEX/CMakeLists.txt ./patches/CMakeLists.patch
 

src/Pdf2Html/pdf2htmlEX/patches/unicode.cc.patch

@@ -0,0 +1,18 @@
+@@ -47,6 +47,8 @@ Unicode unicode_from_font (CharCode code, GfxFont * font)
+         if(cname)
+         {
+             Unicode ou = globalParams->mapNameToUnicodeText(cname);
++            if(ou == '\t')
++                return ' ';
+             if(!is_illegal_unicode(ou))
+                 return ou;
+         }
+@@ -62,6 +64,8 @@ Unicode check_unicode(Unicode const * u, int len, CharCode code, GfxFont * font)
+ 
+     if(len == 1)
+     {
++        if(*u == '\t')
++            return ' ';
+         if(!is_illegal_unicode(*u))
+             return *u;
+     }

src/Pdf2Html/pdf2htmlEX/patches/unicode.h.patch

@@ -1,3 +1,12 @@
+@@ -27,7 +27,7 @@ namespace pdf2htmlEX {
+  *         00(NUL)--09(\t)--0A(\n)--0D(\r)--20(SP)--7F(DEL)--9F(APC)--A0(NBSP)--AD(SHY)--061C(ALM)--1361(Ethiopic word space)
+  * webkit:   [--------------------------------)        [------------------)       [-]
+  * moz:      [--------------------------------)        [---------]                          [-]
+- * p2h:      [--------------------------------)        [------------------]       [-]       [-]         [-]
++ * p2h:      [--------------------------------)        [------------------)       [-]       [-]         [-]
+  *
+  *         200B(ZWSP)--200C(ZWNJ)--200D(ZWJ)--200E(LRM)--200F(RLM)--2028(LSEP)--2029(PSEP)--202A(LRE)--202E(RL0)--2066(LRI)--2069(PDI)
+  * webkit:   [-----------------------------------------------]                                 [----------]
 @@ -39,9 +39,6 @@ namespace pdf2htmlEX {
   * moz:
   * p2h:         [------------------]            [-]           [-]          [-----------------]

tests/E2E.Tests/Resources/CS_cheat_sheet.html

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff65d9e1cc4864dc0db647594c33c01333faa20e0e104379b42ae2b8e9694c0a
-size 1086803
+oid sha256:e020014ff0cab94ab78700278ed7b54852b944ccb366015b1a60ae944e0780d7
+size 1086801