Merge pull request #12 from CoreFiling/feature/switch-to-our-fork

Switch to our fork

Author: ethanbishop

CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.3.0
+
+* Switch to `cfl3` CFL patched fork instead of patching as part of this build.
+  * This improves support for certain font CMaps
+  * Remove `--tounicode` in favour of `--ignore-tounicode`, as `force` is no longer required.
+
 ## 0.2.2
 
 * Patch memory corruption bug due to PNG background images being the incorrect size.

README.md

@@ -28,4 +28,4 @@ docker run corefiling/pdf2html pdf2htmlEX:$version --help
 
 Since pdf2htmlex is licensed under the GPL, this project is too (see the LICENSE.TXT file).
 
-As you can see from the build process, pdf2htmlEX itself is patched by the patches within this project (see [src/Pdf2Html/patches](tree/src/Pdf2Html/patches)), based on a clone of the upstream project tag we are targeting. As such we have not repeated pdf2htmlEX's source code here; you can find it via the link above.
+As you can see from the build process, pdf2htmlEX itself is aquired from our fork of pdf2htmlEX/pdf2htmlEX found here: https://github.com/CoreFiling/pdf2htmlEX/tree/feature/cfl-patches

src/Pdf2Html/Dockerfile

@@ -3,40 +3,12 @@ FROM ubuntu:noble AS build-pdf2htmlex
 
 # Produces a patched pdf2htmlEX using libopenjp 2.7 instead of libjpeg to get JPEG2000 support.
 
-ENV PDF2HTMLEX_BRANCH=
-ENV UNATTENDED="--assume-yes"
-ENV MAKE_PARALLEL="-j 4"
-ENV PDF2HTMLEX_PREFIX=/usr/local
-ENV DEBIAN_FRONTEND=noninteractive
-
 WORKDIR /source
 RUN apt update && apt install -y git patch sudo
-RUN git clone --depth=1 --branch v0.18.8.rc1 https://github.com/pdf2htmlEX/pdf2htmlEX
+RUN git clone --depth=1 --branch 0.18.8.rc1-cfl3 https://github.com/CoreFiling/pdf2htmlEX
 WORKDIR /source/pdf2htmlEX
 
-COPY ./pdf2htmlEX/patches ./patches
-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/BackgroundRenderer/SplashBackgroundRenderer.cc ./patches/SplashBackgroundRenderer.cc.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
-
-RUN ./buildScripts/versionEnvs
-RUN ./buildScripts/reportEnvs
-RUN ./buildScripts/getBuildToolsApt
-RUN ./buildScripts/getDevLibrariesApt
-RUN ./buildScripts/getPoppler
-RUN patch ./poppler/glib/poppler-enums.c.template ./patches/poppler-enums.c.template.patch
-RUN patch ./poppler/glib/poppler-private.h ./patches/poppler-private.h.patch
-RUN ./buildScripts/buildPoppler
-RUN ./buildScripts/getFontforge
-RUN patch ./fontforge/fontforge/tottfgpos.c ./patches/fontforge-tottfgpos.c.patch
-RUN ./buildScripts/buildFontforge
-RUN ./buildScripts/buildPdf2htmlEX
-RUN ./buildScripts/installPdf2htmlEX
+RUN ./buildScripts/buildInstallLocallyApt
 RUN git config user.name "CoreFiling"
 RUN git config user.email "opensource@corefiling.com"
 RUN ./buildScripts/createDebianPackage
@@ -51,7 +23,7 @@ RUN apt update && apt install -y wget
 RUN wget http://archive.ubuntu.com/ubuntu/pool/main/libj/libjpeg-turbo/libjpeg-turbo8_2.0.3-0ubuntu1_amd64.deb
 RUN apt install -y ./libjpeg-turbo8_2.0.3-0ubuntu1_amd64.deb
 COPY --from=build-pdf2htmlex /source/pdf2htmlEX/imageBuild/*.deb /pdf2htmlEX/
-RUN apt install -y libjpeg62 libopenjp2-7 /pdf2htmlEX/pdf2htmlEX-0.18.8.rc1-cfl2-*-x86_64.deb
+RUN apt install -y libjpeg62 libopenjp2-7 /pdf2htmlEX/pdf2htmlEX-0.18.8.rc1-cfl3-*-x86_64.deb
 
 WORKDIR /app
 COPY --from=build /app ./

src/Pdf2Html/Pdf2Html.csproj

@@ -4,7 +4,7 @@
     <TargetFramework>net8.0</TargetFramework>
     <Nullable>enable</Nullable>
     <ImplicitUsings>enable</ImplicitUsings>
-    <Version>0.2.2</Version>
+    <Version>0.3.0</Version>
     <AssemblyName>Pdf2Html</AssemblyName>
     <RootNamespace>Pdf2Html</RootNamespace>
   </PropertyGroup>

src/Pdf2Html/appsettings.json

@@ -6,8 +6,7 @@
     "Printing": false,
     "BgFormat": "svg",
     "SvgNodeCountLimit": 100,
-    "DecomposeLigature": true,
-    "Tounicode": true
+    "DecomposeLigature": true
   },
   "Logging": {
     "LogLevel": {