First usable version

config.ini

@@ -0,0 +1,9 @@
+[Options]
+rainbow_exec = /path/to/rainbow/executable
+custom_filters_folder = /path/to/folder/with/custom/filters
+
+[Filters]
+mxliff = okf_autoxliff
+xliff = okf_autoxliff
+xlf = okf_autoxliff
+xlz = okf_archive

okapi-batch-runner.py

@@ -1,13 +1,12 @@
 import subprocess
 import sys
 import os
-import re
-import io
 import glob
 import configparser
 import xml.etree.ElementTree as ET
 from pathlib import Path
 
+# Function for selection lists
 def select_item(welcome_text, items):
     print(welcome_text+"\n")
     for i, item in enumerate(items):
@@ -26,45 +25,81 @@ def select_item(welcome_text, items):
         print('Error! Please enter one number between 1-{}'.format(len(items)))
         exit()
 
+# Function to get the correct filter for a file
 def get_filter(path):
-    return "filter"
+    extension = os.path.splitext(path)[1][1:]
+    if (extension == ""):
+        return extension
+    else:
+        if (extension in project_config["Filters"]):
+            return project_config["Filters"][extension]
+        else:
+            if (extension in config["Filters"]):
+                return config["Filters"][extension]
+            else:
+                return ""
 
 
+# Load config
 config = configparser.ConfigParser()
 config.read(os.path.join(sys.path[0],"config.ini"))
 rainbow = config["Options"]["rainbow_exec"]
 
-work_directory = sys.argv[1:]
+# Get work directories (ignore 0, which is this Python script)
+work_directories = sys.argv[1:]
 
+# Load project
 list_projects = os.listdir(os.path.join(sys.path[0],"projects"))
-project_folder = os.path.join(sys.path[0],"projects",select_item("Available projects:",list_projects))
+project_dir = os.path.join(sys.path[0],"projects",select_item("Available projects:",list_projects))
-project = os.path.join(project_folder,"project.rnb")
+project = os.path.join(project_dir,"project.rnb")
-
-list_pipelines = [os.path.basename(x) for x in glob.glob(os.path.join(sys.path[0],"projects",project_folder,"*.pln"))]
-pipeline = os.path.join(project_folder,select_item("Available pipelines:",list_pipelines))
 
+# Load project config
 project_config = configparser.ConfigParser()
-project_config.read(os.path.join(project_folder,"project.ini"))
+project_config.read(os.path.join(project_dir,"project.ini"))
 
+# Load pipeline
+list_pipelines = [os.path.basename(x) for x in glob.glob(os.path.join(sys.path[0],"projects",project_dir,"*.pln"))]
+pipeline = os.path.join(project_dir,select_item("Available pipelines:",list_pipelines))
+
+# Build list of files to be processed
 files = []
+files_root = os.getcwd()
 
-for directory in work_directory:
+for directory in work_directories:
     if any(Path(directory).rglob('*.*')):
         for translationfile in Path(directory).rglob('*.*'):
-            filter = get_filter(translationfile)
+            if (translationfile.is_file()):
-            if (filter != ""):
+                filter = get_filter(translationfile)
-                files.append((translationfile,filter))
+                if (filter != ""):
-
+                    relpath = os.path.relpath(translationfile,files_root)
+                    files.append((relpath,filter))
 
+# Parse project
 project_tree = ET.parse(project)
-root = project_tree.getroot()
+project_tree_root = project_tree.getroot()
+fileset = project_tree_root.find("./fileSet[@id='1']")
+fileset_root = project_tree_root.find("./fileSet[@id='1']/root")
+parameters = project_tree_root.find("./parametersFolder")
 
-elem = root.find("./fileSet[@id='1']")
+# Set the parameters folder to the one defined in the config
+fileset_root.set("useCustom","1")
+fileset_root.text = config["Options"]["custom_filters_folder"]
+
+# Set the root of the first fileset to the working folder
+fileset_root.set("useCustom","1")
+fileset_root.text = files_root
+
+# Add files to first fileset
 for item in files:
     new=ET.Element("fi",attrib={"fs":item[1]})
     new.text=str(item[0])
-    elem.append(new)
+    fileset.append(new)
 
-project_tree.write("testproject.rnb",encoding="UTF-8",xml_declaration=True)
+# Write temporary custom project file for Okapi Rainbow
+project_tree.write("temp_project.rnb",encoding="UTF-8",xml_declaration=True)
 
-#subprocess.run([rainbow,"-p",project,"-pln",pipeline,"-np"])
+# Run Okapi Rainbow with the temporary project and the selected pipeline
+subprocess.run([rainbow,"-p","temp_project.rnb","-pln",pipeline,"-np"])
+
+# Remove temporary project file after executing the pipeline
+os.remove("temp_project.rnb") 

projects/Example project/project.ini

@@ -0,0 +1,2 @@
+[Filters]
+txt = okf_plaintext

projects/Example project/project.rnb

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rainbowProject version="4">
+	<fileSet id="1">
+		<root useCustom="0"></root>
+	</fileSet>
+	<fileSet id="2">
+		<root useCustom="0"></root></fileSet>
+	<fileSet id="3">
+		<root useCustom="0"></root>
+	</fileSet>
+	<output>
+		<root use="0"></root>
+		<subFolder use="0"></subFolder>
+		<extension use="1" style="0">.out</extension>
+		<replace use="0" oldText="" newText=""></replace>
+		<prefix use="0"></prefix><suffix use="0"></suffix>
+	</output>
+	<options sourceLanguage="en" sourceEncoding="UTF-8" targetLanguage="ca" targetEncoding="UTF-8"></options>
+	<parametersFolder useCustom="0"></parametersFolder>
+	<utilities xml:spaces="preserve"></utilities>
+</rainbowProject>

projects/Example project/wordcount.pln

@@ -0,0 +1,50 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rainbowPipeline version="1"><step class="net.sf.okapi.steps.common.RawDocumentToFilterEventsStep"></step>
+<step class="net.sf.okapi.steps.wordcount.WordCountStep">#v1
+countInBatch.b=true
+countInBatchItems.b=true
+countInDocuments.b=true
+countInSubDocuments.b=false
+countInGroups.b=false
+bufferSize.i=0</step>
+<step class="net.sf.okapi.steps.wordcount.CharacterCountStep">#v1
+countInBatch.b=true
+countInBatchItems.b=true
+countInDocuments.b=true
+countInSubDocuments.b=false
+countInGroups.b=false
+bufferSize.i=0</step>
+<step class="net.sf.okapi.steps.repetitionanalysis.RepetitionAnalysisStep">#v1
+fuzzyThreshold.i=100
+maxHits.i=20</step>
+<step class="net.sf.okapi.steps.scopingreport.ScopingReportStep">#v1
+projectName=My Project
+customTemplateURI=
+customTemplateString=
+outputPath=${rootDir}/scoping_report.html
+countAsNonTranslatable_GMXProtected.b=true
+countAsNonTranslatable_GMXExactMatched.b=true
+countAsNonTranslatable_GMXLeveragedMatched.b=false
+countAsNonTranslatable_GMXRepetitionMatched.b=false
+countAsNonTranslatable_GMXFuzzyMatch.b=false
+countAsNonTranslatable_GMXAlphanumericOnlyTextUnit.b=true
+countAsNonTranslatable_GMXNumericOnlyTextUnit.b=true
+countAsNonTranslatable_GMXMeasurementOnlyTextUnit.b=true
+countAsNonTranslatable_ExactUniqueIdMatch.b=true
+countAsNonTranslatable_ExactPreviousVersionMatch.b=true
+countAsNonTranslatable_ExactLocalContextMatch.b=false
+countAsNonTranslatable_ExactDocumentContextMatch.b=false
+countAsNonTranslatable_ExactStructuralMatch.b=false
+countAsNonTranslatable_ExactMatch.b=false
+countAsNonTranslatable_ExactTextOnlyPreviousVersionMatch.b=false
+countAsNonTranslatable_ExactTextOnlyUniqueIdMatch.b=false
+countAsNonTranslatable_ExactTextOnly.b=false
+countAsNonTranslatable_ExactRepaired.b=false
+countAsNonTranslatable_FuzzyPreviousVersionMatch.b=false
+countAsNonTranslatable_FuzzyUniqueIdMatch.b=false
+countAsNonTranslatable_FuzzyMatch.b=false
+countAsNonTranslatable_FuzzyRepaired.b=false
+countAsNonTranslatable_PhraseAssembled.b=false
+countAsNonTranslatable_MT.b=false
+countAsNonTranslatable_Concordance.b=false</step>
+</rainbowPipeline>