summaryrefslogtreecommitdiffstats
path: root/sc/workben
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 09:06:44 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 09:06:44 +0000
commited5640d8b587fbcfed7dd7967f3de04b37a76f26 (patch)
tree7a5f7c6c9d02226d7471cb3cc8fbbf631b415303 /sc/workben
parentInitial commit. (diff)
downloadlibreoffice-upstream.tar.xz
libreoffice-upstream.zip
Adding upstream version 4:7.4.7.upstream/4%7.4.7upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'sc/workben')
-rw-r--r--sc/workben/cache.py87
-rw-r--r--sc/workben/celltrans/keywords_utf16.txtbin0 -> 1826 bytes
-rw-r--r--sc/workben/celltrans/parse.py202
3 files changed, 289 insertions, 0 deletions
diff --git a/sc/workben/cache.py b/sc/workben/cache.py
new file mode 100644
index 000000000..ba96abe97
--- /dev/null
+++ b/sc/workben/cache.py
@@ -0,0 +1,87 @@
+# -*- Mode: python; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+#
+
+import sys
+import struct
+
+column_block_type = {
+ 0 : "empty block",
+ 1 : "numeric block",
+ 2 : "string block"
+ }
+
+
+def parse_block(data, index):
+ start_row = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ data_size = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ block_type = struct.unpack('B', data[index:index+1])[0]
+ index += 1
+ vals = {}
+ if block_type == 1:
+ # numeric block
+ for i in range(data_size):
+ vals[start_row + i] = struct.unpack('d', data[index:index+8])[0]
+ index += 8
+ elif block_type == 2:
+ # string block
+ for i in range(data_size):
+ str_length = struct.unpack('i', data[index:index+4])[0]
+ index += 4
+ vals[start_row + i] = data[index:index+str_length].decode("utf-8")
+ index += str_length
+ elif block_type == 3:
+ # formula block
+ read_rows = 0
+ while read_rows < data_size:
+ formula_group_size = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ str_length = struct.unpack('i', data[index:index+4])[0]
+ index += 4
+ vals[start_row + read_rows] = (data[index:index+str_length].decode("utf-8"), "formula group length %i"% formula_group_size)
+ read_rows += formula_group_size
+ index += str_length
+
+ return index, data_size, vals
+
+
+def parse_column(data, index):
+ column_index = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ column_entries = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ imported_columns = 0
+ column_values = {}
+ while imported_columns < column_entries:
+ index, block_size, vals = parse_block(data, index)
+ imported_columns += block_size
+ column_values.update(vals)
+ return index, column_values
+
+def parse_columns(data, index):
+ column_count = struct.unpack('Q', data[index:index+8])[0]
+ index += 8
+ columns = {}
+ for i in range(column_count):
+ index, column_values = parse_column(data, index)
+ columns[i] = column_values
+
+ return columns
+
+def main():
+ filename = sys.argv[1]
+ with open(filename, "rb") as f:
+ content = f.read()
+ index = 0
+ columns = parse_columns(content, index)
+ print(columns)
+
+if __name__ == "__main__":
+ main()
+
+# vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sc/workben/celltrans/keywords_utf16.txt b/sc/workben/celltrans/keywords_utf16.txt
new file mode 100644
index 000000000..3c9b12d0d
--- /dev/null
+++ b/sc/workben/celltrans/keywords_utf16.txt
Binary files differ
diff --git a/sc/workben/celltrans/parse.py b/sc/workben/celltrans/parse.py
new file mode 100644
index 000000000..937d92f64
--- /dev/null
+++ b/sc/workben/celltrans/parse.py
@@ -0,0 +1,202 @@
+#!/usr/bin/env python
+#
+# This file is part of the LibreOffice project.
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+#
+# This file incorporates work covered by the following license notice:
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed
+# with this work for additional information regarding copyright
+# ownership. The ASF licenses this file to you under the Apache
+# License, Version 2.0 (the "License"); you may not use this file
+# except in compliance with the License. You may obtain a copy of
+# the License at http://www.apache.org/licenses/LICENSE-2.0 .
+#
+
+import sys
+
+localeNames = {'fr': 'French', 'hu': 'Hungarian', 'de': 'German'}
+def getLocaleName (code):
+ global localeNames
+ if code in localeNames:
+ return localeNames[code]
+ else:
+ return "(unknown locale)"
+
+def getAscii (ords):
+ ascii = ''
+ for c in ords:
+ ascii += chr(c)
+ return ascii
+
+class LocaleData(object):
+ def __init__ (self, locale):
+ self.locale = locale
+ self.funcList = {}
+
+ def addKeywordMap (self, funcName, localeName, engName):
+ if not funcName in self.funcList:
+ self.funcList[funcName] = []
+
+ self.funcList[funcName].append([localeName, engName])
+
+ def getLocaleFuncVarName (self, func, pair):
+ return func.lower() + "_" + getAscii(pair[1]).lower() + "_" + self.locale
+
+ def dumpCode (self):
+ chars = ""
+
+ # locale output
+ chars += "// " + "-"*75 + "\n"
+ chars += "// %s language locale (automatically generated)\n"%getLocaleName(self.locale)
+ chars += "// " + "-"*75 + "\n"
+ chars += "static const Locale a" + self.locale.capitalize() + "(OUString(\""
+ chars += self.locale
+ chars += "\"), OUString(), OUString());\n\n"
+
+ # pre instantiations of localized function names.
+ funcs = sorted(self.funcList.keys())
+ chars += "// pre instantiations of localized function names\n"
+ for func in funcs:
+ for item in self.funcList[func]:
+ chars += "static const sal_Unicode " + self.getLocaleFuncVarName(func, item) + "[] = {\n"
+ chars += " "
+ isFirst = True
+ # Dump the UTF-16 bytes.
+ for uval in item[0]:
+ if isFirst:
+ isFirst = False
+ else:
+ chars += ", "
+ chars += "0x%.4X"%uval
+
+ # Don't forget to null-terminate the string.
+ if not isFirst:
+ chars += ", "
+ chars += "0x0000"
+
+ chars += "};\n"
+
+ # map item instantiations
+ chars += "\n"
+ chars += "static const TransItem p" + self.locale.capitalize() + "[] = {\n"
+ for func in funcs:
+ for item in self.funcList[func]:
+ chars += " "
+ chars += "{%s, \"%s\", %s},\n"%(self.getLocaleFuncVarName(func, item),
+ getAscii(item[1]),
+ "oc"+func.capitalize())
+
+ chars += " {NULL, NULL, ocNone}\n"
+ chars += "};\n\n"
+
+ # addToMap call
+ chars += "addToMap(%s, %s);\n"%(
+ "p"+self.locale.capitalize(), "a"+self.locale.capitalize())
+
+ return chars
+
+class Parser(object):
+
+ def __init__ (self, args):
+ # default input & output files.
+ self.infile = "./keywords_utf16.txt"
+ self.outfile = "../../source/core/tool/cellkeywords.inl"
+
+ if len(args) >= 2:
+ self.infile = args[1]
+ if len(args) >= 3:
+ self.outfile = args[2]
+
+ def getDByte (self):
+ # Assume little endian.
+ bh = self.bytes[self.i]
+ bl = self.bytes[self.i+1]
+ try:
+ dbyte = ord(bl)*256 + ord(bh)
+ except:
+ dbyte = bl*256 + bh
+ self.i += 2
+ return dbyte
+
+ def parseLine (self):
+ buf = []
+ while self.i < self.size:
+ dbyte = self.getDByte()
+ if dbyte == 0x000A:
+ break
+ buf.append(dbyte)
+ return buf
+
+ def dumpBuf (self, buf, linefeed=True):
+ for item in buf:
+ sys.stdout.write(chr(item))
+ if linefeed:
+ print ('')
+
+ def parse (self):
+
+ file = open(self.infile, 'rb')
+ self.bytes = file.read()
+ file.close()
+
+ self.size = len(self.bytes)
+ self.i = 0
+
+ localeList = [] # stores an array of locale data objects.
+ funcName = None
+ word = []
+ wordPair = []
+
+ while self.i < self.size:
+ dbyte = self.getDByte()
+ if dbyte == 0xFEFF and self.i == 2:
+ # unicode signature - ignore it.
+ pass
+ elif dbyte == 0x0024:
+ # $ - locale name
+ buf = self.parseLine()
+ locale = getAscii(buf)
+ localeList.append(LocaleData(locale))
+
+ elif dbyte == 0x0040:
+ # @ - function name
+ buf = self.parseLine()
+ funcName = getAscii(buf)
+
+ elif dbyte == 0x002C:
+ # , - comma separator
+ if len(word) > 0:
+ wordPair.append(word)
+ word = []
+ elif dbyte == 0x000A:
+ # linefeed
+ if len(word) > 0:
+ wordPair.append(word)
+ word = []
+ if len(wordPair) >= 2:
+ localeList[-1].addKeywordMap(funcName, wordPair[0], wordPair[1])
+ wordPair = []
+ elif dbyte in [0x0009, 0x0020]:
+ # whitespace - ignore it.
+ pass
+ else:
+ word.append(dbyte)
+
+ chars = "// This file has been automatically generated. Do not hand-edit this!\n"
+ for obj in localeList:
+ chars += "\n" + obj.dumpCode()
+
+ # Write to output file.
+ file = open(self.outfile, 'w')
+ file.write(chars)
+ file.close()
+
+if __name__=='__main__':
+ parser = Parser(sys.argv)
+ parser.parse()
+