tools/common.py (d6bb2a3) - fs-words.git

common.py

import json as _json
import os as _os
import re as _re

def dokuwiki_to(data):
	content = ""
	content += ("  * type: %s\n" % (data["type"]))
	content += ("  * description: %s\n" % ("?" if (data["description"] is None) else data["description"]))
	content += ("  * tags\n")
	for tag in data["tags"]:
		content += ("    * %s\n" % (tag))
	content += ("  * translations\n")
	for (language , lemmata) in data["translations"].items():
		content += ("    * %s\n" % (language))
		for lemma in lemmata:
			content += ("      * %s\n" % (lemma))
	return content

def dokuwiki_from(content):
	data = {}
	state = "type"
	lines = content.split("\n")
	for line in lines:
		if (line != ""):
			if (state == "type"):
				result = _re.match("^  \\* type: (.*)$", line)
				if (result is not None):
					data["type"] = result.group(1)
					state = "description"
				else:
					raise ValueError("type expected in line '%s' while being in state '%s'" % (line, state))
			elif (state == "description"):
				result = _re.match("^  \\* description: (.*)$", line)
				if (result is not None):
					data["description"] = (None if (result.group(1) == "?") else result.group(1))
					state = "tags"
				else:
					raise ValueError("description expected in line '%s' while being in state '%s'" % (line, state))
			elif (state == "tags"):
				result = _re.match("^  \\* tags$", line)
				if (result is not None):
					data["tags"] = []
					state = "tagentry"
				else:
					raise ValueError("tags expected in line '%s' while being in state '%s'" % (line, state))
			elif (state == "tagentry"):
				result = _re.match("^    \\* (.*)$", line)
				if (result is not None):
					data["tags"].append(result.group(1))
					state = "tagentry"
				else:
					result = _re.match("^  \\* translations$", line)
					if (result is not None):
						data["translations"] = {}
						state = "language"
					else:
						raise ValueError("tag or translations expected in line '%s' while being in state '%s'" % (line, state))
			elif (state == "language"):
				result = _re.match("^    \\* (.*)$", line)
				if (result is not None):
					language = result.group(1)
					data["translations"][language] = []
					state = "lemma"
				else:
					raise ValueError("language expected in line '%s' while being in state '%s'" % (line, state))
			elif (state == "lemma"):
				result = _re.match("^      \\* (.*)$", line)
				if (result is not None):
					lemma = result.group(1)
					data["translations"][language].append(lemma)
					state = "lemma"
				else:
					result = _re.match("^    \\* (.*)$", line)
					if (result is not None):
						language = result.group(1)
						data["translations"][language] = []
						state = "lemma"
					else:
						raise ValueError("language or lemma expected in line '%s' while being in state '%s'" % (line, state))
			else:
				raise ValueError("unhandled state '%s'" % (state))
	return data

def json_to(data):
	content = _json.dumps(data, indent = "\t", ensure_ascii = False)
	return content

def json_from(content):
	data = _json.loads(content)
	return data

def filemap(folder_from, convert_from, folder_to, convert_to, namemapper):
	for name_from in _os.listdir(folder_from):
		path_from = _os.path.join(folder_from, name_from)
		handle_from = open(path_from, "r")
		content_from = handle_from.read()
		handle_from.close()
		data = convert_from(content_from)
		name_to = namemapper(name_from)
		path_to = _os.path.join(folder_to, name_to)
		content_to = convert_to(data)
		handle_to = open(path_to, "w")
		handle_to.write(content_to)
		handle_to.close()

fs-words.git

moved to flat files