Docker fixes

Dockerfile

@@ -5,10 +5,12 @@ MAINTAINER Konstantin Baierer <[email protected]>
 EXPOSE 8080
 ADD . /ocr-fileformat
 WORKDIR /ocr-fileformat
-RUN apk add --no-cache openjdk8-jre php7 php7-json py-lxml git make ca-certificates wget \
+RUN apk add --no-cache openjdk8-jre php7 php7-json py-lxml git make ca-certificates wget bash \
     && update-ca-certificates \
     && make install \
     && mv web /ocr-fileformat-web \
     && rm -rf /ocr-fileformat \
     && apk del git make wget
+VOLUME /data
+WORKDIR /data
 CMD php7 -S $(hostname -i):8080 -t /ocr-fileformat-web

Makefile

@@ -1,5 +1,6 @@
 PKG_NAME = ocr-fileformat
 PKG_VERSION = 0.1.0
+DOCKER_IMAGE = ubma/ocr-fileformat
 
 CP = cp -r
 LN = ln -sf
@@ -73,6 +74,9 @@ clean:
 realclean: clean
 	$(MAKE) -C vendor clean
 
+docker:
+	docker build -t "$(DOCKER_IMAGE)" .
+
 release:
 	$(RM) $(PKG_NAME)_$(PKG_VERSION)
 	$(MKDIR) $(PKG_NAME)_$(PKG_VERSION)

README.md

@@ -1,15 +1,18 @@
 # ocr-fileformat
 
-[![Build Status](https://travis-ci.org/UB-Mannheim/ocr-fileformat.svg?branch=master)](https://travis-ci.org/UB-Mannheim/ocr-fileformat)
+[![Build Status](https://travis-ci.org/UB-Mannheim/ocr-fileformat.svg?branch=master)](https://travis-ci.org/UB-Mannheim/ocr-fileformat) [![ocr-fileformat Docker build](https://img.shields.io/docker/automated/ubma/ocr-fileformat.svg?maxAge=2592000?style=plastic)](https://hub.docker.com/r/ubma/ocr-fileformat)
 
 Validate and transform between OCR file formats (hOCR, ALTO, PAGE, FineReader)
 
 ![Screenshot GUI](./screenshot.png)
 
-<!-- vim :GenTocGFM -->
+<!-- BEGIN-MARKDOWN-TOC -->
 * [Installation](#installation)
+	* [Docker](#docker)
+	* [System-wide](#system-wide)
 * [Usage](#usage)
 	* [CLI](#cli)
+	* [GUI](#gui)
 	* [API](#api)
 * [Transformation](#transformation)
 	* [Transformation CLI](#transformation-cli)
@@ -23,8 +26,31 @@ Validate and transform between OCR file formats (hOCR, ALTO, PAGE, FineReader)
 	* [Supported Validation Formats](#supported-validation-formats)
 * [License](#license)
 
+<!-- END-MARKDOWN-TOC -->
+
 ## Installation
 
+### Docker
+
+You can run the [command line scripts](#cli) and [web interface](#gui) as a
+[Docker container](https://hub.docker.com/r/ubma/ocr-fileformat), you only need
+Docker installed.
+
+To start the web interface on [http://localhost:8080](http://localhost:8080):
+
+```sh
+docker run --rm -it -p 8080:8080 ubma/ocr-fileformat
+```
+
+To run the command line scripts, mount the directory containing your input
+files into the container's `/data` directory:
+
+```sh
+docker run --rm -it -v "$PWD:/data" ubma/ocr-fileformat ocr-transform alto2.0 hocr somefile.alto
+```
+
+### System-wide
+
 To install system-wide to `/usr/local`:
 
 ```sh
@@ -63,6 +89,11 @@ script (CLI), using a web interface (GUI) or in you own tools (API)
 * [`ocr-transform`](./blob/master/bin/ocr-transform.sh): Transformation of OCR output between OCR formats
 * [`ocr-validate`](./blob/master/bin/ocr-validate.sh): Validation of OCR output against OCR format schemas
 
+### GUI
+
+The web interface is for testing validation and transformations. You can upload
+a file or select an input file by URL.
+
 ### API
 
 * [`$PREFIX/share/ocr-fileformat/xslt`](./xslt) - XSLT stylesheets

lib.sh

@@ -48,7 +48,7 @@ declare -Ax OCR_VALIDATORS=()
 setup_transformations () {
     declare -a transformers=($(
         find "$SHAREDIR/xslt" "$SHAREDIR/script/transform" \
-            ! -type d \( -name '*.xsl' -or -executable \) \
+            ! -type d \( -name '*.xsl' -or -perm -005 \) \
         ))
     local in_fmt out_fmt
     for path in "${transformers[@]}";do
@@ -69,8 +69,8 @@ setup_transformations () {
 setup_validations () {
     declare -a validators=($(
         find "$SHAREDIR/xsd" "$SHAREDIR/script/validate" \
-            ! -type d \( -name '*.xsd' -or -executable \) \
-            |sort -h))
+            ! -type d \( -name '*.xsd' -or -perm -005 \) \
+            |sort))
     local path fmt
     for path in "${validators[@]}";do
         fmt=${path##*/}
@@ -90,7 +90,7 @@ setup
 # show_schemas ()
 show_schemas() {
     local schema schemagroup
-    declare -a sorted=($(IFS=$'\n'; echo "${!OCR_VALIDATORS[*]}"|sort -V))
+    declare -a sorted=($(IFS=$'\n'; echo "${!OCR_VALIDATORS[*]}"|sort -t- -nk2  -k1))
     for schema in "${sorted[@]}";do
         [[ -n "$schemagroup" && "$schemagroup" != ${schema%%-*} ]] && echo
         echo -n "$schema "
@@ -106,7 +106,7 @@ show_transformations() {
         for out_fmt in "${out_fmts[@]}";do
             echo "${in_fmt} ${out_fmt}";
         done
-    done|sort -V
+    done|sort
 }
 
 # show_saxon_options ()

vendor/Makefile

@@ -1,7 +1,7 @@
 CP = cp -rv
 MKDIR = mkdir -p
 RM = rm -rfv
-UNZIP = unzip -u
+UNZIP = unzip -o
 WGET = wget --progress=bar:force --no-verbose
 GIT_CLONE = git clone --depth 1