def getRanges(self):
progressBar = ProgressBar(self.unoObjs, "Finding text...")
progressBar.show()
progressBar.updateBeginning()
textSearch = TextSearch(self.unoObjs, progressBar)
textSearch.setConfig(self.config.searchConfig)
try:
if self.config.whichScope == 'WholeDoc':
textSearch.scopeWholeDocTraverse()
elif self.config.whichScope == 'Selection':
textSearch.scopeSelection()
elif self.config.whichScope == 'Language':
textSearch.scopeLocale()
elif self.config.whichScope == 'ParaStyle':
textSearch.scopeParaStyle()
elif self.config.whichScope == 'CharStyle':
textSearch.scopeCharStyle()
elif self.config.whichScope == 'Font':
textSearch.scopeFont()
elif self.config.whichScope == 'SFMs':
textSearch.scopeSFMs()
else:
raise exceptions.LogicError(
"Unexpected value %s", self.config.whichScope)
progressBar.updateFinishing()
except exceptions.MessageError as exc:
raise exc
finally:
progressBar.close()
return textSearch.getRanges()
def __init__(self, unoObjs):
if self.__class__ is FileReader:
# The base class should not be instantiated.
raise NotImplementedError()
self.unoObjs = unoObjs
self.msgbox = MessageBox(unoObjs)
self.progressBar = ProgressBar(unoObjs, "Loading data...")
self.data = None # typically a list or dict
self.dom = None
self.filepath = ""
def setUp(self):
unoObjs = testutil.unoObjsForCurrentDoc()
fileconfig = fileitemlist.WordListFileItem(None)
docReader = DocReader(fileconfig, unoObjs, -1)
docReader.loadDoc(self.INFILE)
self.unoObjs = docReader.doc
testutil.stored.doc = self.unoObjs.document
self.progressBar = ProgressBar(self.unoObjs, "TestSearch")
def findOccurrences(self, abbrevList):
"""Modifies abbrevList."""
progressBar = ProgressBar(self.unoObjs, "Searching for occurrences...")
progressBar.show()
progressBar.updateBeginning()
progressRange = ProgressRange(ops=len(abbrevList), pbar=progressBar)
for itemPos in range(0, len(abbrevList)):
search = self.unoObjs.document.createSearchDescriptor()
search.SearchString = abbrevList[itemPos].abbrevText
search.SearchCaseSensitive = False
search.SearchWords = True
selectionsFound = self.unoObjs.document.findAll(search)
occurrences = selectionsFound.getCount()
abbrevList.setOccurrences(itemPos, occurrences)
progressRange.update(itemPos)
progressBar.updateFinishing()
progressBar.close()
def outputList(self, wordList, progressBarWriter):
"""Sends output to the Calc spreadsheet.
Takes a list of app.wordlist.WordInList.
"""
logger.debug(util.funcName('begin'))
outputter = SpreadsheetOutput(self.unoObjs)
self.listDoc = outputter.createSpreadsheet()
self.msgbox = MessageBox(self.listDoc)
self.sheet = self.listDoc.sheets.getByIndex(0)
progressBarCalc = ProgressBar(self.listDoc, "Generating List...")
progressBarCalc.show()
self.progressRanges = ProgressRanges(
[progressBarWriter, progressBarCalc])
self.progressRanges.initRanges(progressBarWriter.getPercent() + 20, 95,
len(wordList))
self.progressRanges.updateStart()
try:
self._outputList(wordList)
self.progressRanges.updateFinishing()
finally:
self.progressRanges.closeBars()
logger.debug(util.funcName('end'))
def generateList(self, punctToRemove, normForm, outputToCalc=True):
"""Harvest words from various files.
If outputToCalc is True, then output a word list in Calc.
"""
logger.debug(util.funcName('begin'))
all_words_read = []
self.progressBar = ProgressBar(self.unoObjs, "Reading...")
self.progressBar.show()
self.progressBar.updateBeginning()
progressRange = ProgressRange(
ops=len(self.fileItems), pbar=self.progressBar)
try:
for fileItemIndex, fileItem in enumerate(self.fileItems):
try:
new_words = self._harvestWords(fileItem)
all_words_read.extend(new_words)
logger.debug("Word count: %d", len(all_words_read))
except (exceptions.DataNotFoundError,
exceptions.FileAccessError) as exc:
self.msgbox.displayExc(exc)
progressRange.update(fileItemIndex)
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
self.progressBar = ProgressBar(self.unoObjs, "Sorting...")
self.progressBar.show()
self.progressBar.updateBeginning()
try:
splitByWhitespace = True
if len(self.fileItems) > 0:
splitByWhitespace = self.fileItems[0].splitByWhitespace
self.words = organizeList(
all_words_read, punctToRemove, splitByWhitespace, normForm,
self.progressBar)
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
if self.words or len(self.fileItems) == 0:
if outputToCalc:
self.progressBar = ProgressBar(
self.unoObjs, "Generating List...")
self.progressBar.show()
self.progressBar.updateBeginning()
try:
self._generateCalcList()
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
else:
self.msgbox.display("Found %d words.", len(self.words))
else:
self.msgbox.display("Did not find any words for the list.")
class FileReader:
"""Abstract base class for XML file readers.
The methods beginning with a single underscore are intended to only be
called from the base class.
"""
SUPPORTED_FORMATS = [] # list of tuples of name, text description
def __init__(self, unoObjs):
if self.__class__ is FileReader:
# The base class should not be instantiated.
raise NotImplementedError()
self.unoObjs = unoObjs
self.msgbox = MessageBox(unoObjs)
self.progressBar = ProgressBar(unoObjs, "Loading data...")
self.data = None # typically a list or dict
self.dom = None
self.filepath = ""
@classmethod
def supportedNames(cls):
names = [name for name, desc in cls.SUPPORTED_FORMATS]
return names
def read(self):
logger.debug(util.funcName('begin'))
if self.progressBar:
self.progressBar.show()
self.progressBar.updateBeginning()
self.progressBar.updatePercent(20)
self._initData()
try:
self._read()
self._verifyDataFound()
if self.progressBar:
self.progressBar.updateFinishing()
finally:
if self.progressBar:
self.progressBar.close()
logger.debug(util.funcName('end'))
return self.data
def _initData(self):
# All derived classes should implement this method.
raise NotImplementedError()
def _read(self):
# All derived classes should implement this method.
raise NotImplementedError()
def _verifyDataFound(self):
"""Derived classes should override if they don't want this check to
be performed.
"""
if not self.data:
raise exceptions.DataNotFoundError(
"Did not find any data in file %s", self.filepath)
def getSuggestions(self):
"""Get suggested ref numbers. Intended for linguistic examples only,
so derived classes are not required to override this method.
"""
return []
def make(self):
logger.debug(util.funcName('begin'))
progressBar = ProgressBar(self.unoObjs, "Getting data...")
progressBar.show()
progressBar.updateBeginning()
try:
columnOrder = ColumnOrder(self.userVars)
columnOrder.loadUserVars()
changeList = getChangeList(self.unoObjs, columnOrder)
progressBar.updateFinishing()
except exceptions.DocAccessError:
self.msgbox.display("Error reading spreadsheet.")
progressBar.close()
progressBar = ProgressBar(self.unoObjs, "Saving file...")
progressBar.show()
progressBar.updatePercent(50)
if self.exportType == "ReplacementCCT":
outputter = CCT_Writer(self.filepath)
outputter.writeSimpleReplacements(changeList)
elif self.exportType == "SFM_CCT":
outputter = CCT_Writer(self.filepath)
outputter.writeComplete(changeList, self.sfMarkers)
elif self.exportType == "XSLT":
outputter = XSLT_Writer(self.filepath)
outputter.write(changeList, self.xpathExprs, self.matchPartial)
progressBar.updateFinishing()
progressBar.close()
logger.debug(util.funcName('end'))
class WordList:
def __init__(self, writerUnoObjs, fileItems, columnOrder, userVars):
self.unoObjs = writerUnoObjs
self.fileItems = fileItems # FileItemList of WordListFileItem
self.columnOrder = columnOrder
self.userVars = userVars
self.msgbox = MessageBox(self.unoObjs)
self.words = []
self.progressBar = None
def generateList(self, punctToRemove, normForm, outputToCalc=True):
"""Harvest words from various files.
If outputToCalc is True, then output a word list in Calc.
"""
logger.debug(util.funcName('begin'))
all_words_read = []
self.progressBar = ProgressBar(self.unoObjs, "Reading...")
self.progressBar.show()
self.progressBar.updateBeginning()
progressRange = ProgressRange(
ops=len(self.fileItems), pbar=self.progressBar)
try:
for fileItemIndex, fileItem in enumerate(self.fileItems):
try:
new_words = self._harvestWords(fileItem)
all_words_read.extend(new_words)
logger.debug("Word count: %d", len(all_words_read))
except (exceptions.DataNotFoundError,
exceptions.FileAccessError) as exc:
self.msgbox.displayExc(exc)
progressRange.update(fileItemIndex)
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
self.progressBar = ProgressBar(self.unoObjs, "Sorting...")
self.progressBar.show()
self.progressBar.updateBeginning()
try:
splitByWhitespace = True
if len(self.fileItems) > 0:
splitByWhitespace = self.fileItems[0].splitByWhitespace
self.words = organizeList(
all_words_read, punctToRemove, splitByWhitespace, normForm,
self.progressBar)
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
if self.words or len(self.fileItems) == 0:
if outputToCalc:
self.progressBar = ProgressBar(
self.unoObjs, "Generating List...")
self.progressBar.show()
self.progressBar.updateBeginning()
try:
self._generateCalcList()
self.progressBar.updateFinishing()
finally:
self.progressBar.close()
else:
self.msgbox.display("Found %d words.", len(self.words))
else:
self.msgbox.display("Did not find any words for the list.")
def _harvestWords(self, fileItem):
"""Harvest words from the specified file."""
fileType = fileItem.filetype # short variable name
logger.debug(util.funcName(args=fileType))
words = []
if fileType in WordsReader.supportedNames():
reader = WordsReader(fileItem, self.unoObjs)
words = reader.read()
elif fileType in SFM_Reader.supportedNames():
reader = SFM_Reader(fileItem, self.unoObjs)
words = reader.read()
elif fileType in InterlinReader.supportedNames():
config = fileitemlist.InterlinInputSettings(self.userVars)
config.showMorphLine2 = True
config.separateMorphColumns = True
lingExFileItem = fileitemlist.LingExFileItem(self.userVars)
lingExFileItem.filepath = fileItem.filepath
config.fileList.addItem(lingExFileItem)
reader = InterlinReader(self.unoObjs, self.userVars, config)
words = reader.grabWords(fileItem.thingsToGrab)
elif fileType in PhonReader.supportedNames():
config = lingex_structs.PhonInputSettings(self.userVars)
config.filepath = fileItem.filepath
config.phoneticWS = fileItem.writingSystem
config.isLexemePhonetic = True
phonUserVars = UserVars(
Prefix.PHONOLOGY, self.unoObjs.document, logger)
if phonUserVars.get("FlexLexeme") == 'phonemic':
config.isLexemePhonetic = False
reader = PhonReader(self.unoObjs, self.userVars, config)
words = reader.grabWords(fileItem.thingsToGrab)
elif fileType in DocReader.supportedNames():
settings = TextSearchSettings()
settings.load_userVars(self.userVars)
reader = DocReader(fileItem, self.unoObjs, settings.matchesLimit)
words = reader.read()
elif fileType in CalcFileReader.supportedNames():
reader = CalcFileReader(self.unoObjs)
reader.setFileConfig(fileItem)
words = reader.read()
return words
def _generateCalcList(self):
"""Generate list in calc."""
listOutput = WordlistIO(self.unoObjs, self.columnOrder)
listOutput.outputList(self.words, self.progressBar)
msgbox = listOutput.getMsgbox() # for Calc spreadsheet
## Copy some user vars for the Spelling component.
userVarsSp = UserVars(
Prefix.SPELLING, self.unoObjs.document, logger)
varname = "HasSettings"
userVarsSp.store(varname, self.userVars.get(varname))
columnOrderSp = ColumnOrder(userVarsSp)
columnOrderSp.sortOrder = self.columnOrder.sortOrder
columnOrderSp.storeUserVars()
# Initialize some user vars for Calc dialogs. We do this here
# to reset properly if a new word list is made.
self.userVars.store("ConvSourceColumn",
self.columnOrder.getColLetter('colWord'))
self.userVars.store("ConvTargetColumn",
self.columnOrder.getColLetter('colConv1'))
userVarsSp.store("CurrentRow", "")
msgbox.display("Made list of %d words.", len(self.words))
def doConversions_draw(self):
"""For converting data in a Draw doc."""
logger.debug(util.funcName('begin'))
## Start progress bar
progressBar = ProgressBar(self.unoObjs, "Converting...")
progressBar.show()
progressBar.updateBeginning()
## Find the text ranges
shapeSearch = ShapeSearch(self.unoObjs, progressBar)
shapeSearch.setConfig(self.config.searchConfig)
try:
if self.config.whichScope == 'WholeDoc':
shapeSearch.scopeWholeDoc()
elif self.config.whichScope == 'Selection':
shapeSearch.scopeSelection()
elif self.config.whichScope == 'Font':
shapeSearch.scopeFont()
else:
raise exceptions.LogicError("Unexpected value %s",
self.config.whichScope)
except (exceptions.RangeError, exceptions.LogicError) as exc:
self.msgbox.displayExc(exc)
progressBar.close()
return
rangesFound = shapeSearch.getRanges()
if progressBar.getPercent() < 40:
progressBar.updatePercent(40)
## Do the changes to those ranges
textChanger = TextChanger(self.unoObjs, progressBar,
self.changerSettings)
if self.secCall.config.convName:
textChanger.setConverterCall(self.secCall)
textChanger.setFontToChange(self.config.targetFont)
# Apparently, if we change text in front of a range in Draw,
# the range can move. So, start from the end and work backwards.
rangesFound.reverse()
numDataChanges, numStyleChanges = textChanger.doChanges(
rangesFound, self.config.askEach)
progressBar.updateFinishing()
progressBar.close()
## Display results
paragraphsFound = len(rangesFound)
if paragraphsFound == 0:
self.msgbox.display("Did not find scope of change.")
elif numDataChanges == 0:
if numStyleChanges == 0:
self.msgbox.display("No changes.")
else:
plural = "" if numStyleChanges == 1 else "s"
# add "s" if plural
self.msgbox.display(
"No changes, but modified style of %d paragraph%s.",
numStyleChanges, plural)
elif paragraphsFound == 1:
plural = "" if numDataChanges == 1 else "s" # add "s" if plural
self.msgbox.display("Made %d change%s.", numDataChanges, plural)
else:
plural = "" if numDataChanges == 1 else "s" # add "s" if plural
self.msgbox.display("Found %d paragraphs and made %d change%s.",
paragraphsFound, numDataChanges, plural)
def doConversions_calc(self, sourceCol, destCol, skipFirstRow):
"""For converting data in a Calc spreadsheet."""
logger.debug(util.funcName('begin'))
## Start progress bar
progressBar = ProgressBar(self.unoObjs, "Converting...")
progressBar.show()
progressBar.updateBeginning()
## Get list of words from source column
# (just strings are enough, no need for a special object)
reader = SpreadsheetReader(self.unoObjs)
try:
inputList = reader.getColumnStringList(sourceCol, skipFirstRow)
except exceptions.DocAccessError:
self.msgbox.display("Error reading spreadsheet.")
progressBar.close()
if len(inputList) == 0:
self.msgbox.display("Did not find anything in column %s.",
sourceCol)
progressBar.close()
return
if progressBar.getPercent() < 40:
progressBar.updatePercent(40)
## Convert
outList = []
problems = False
numDataChanges = 0
for inValue in inputList:
try:
outValue = self.secCall.convert(inValue)
outList.append(outValue)
if outValue != inValue:
numDataChanges += 1
except exceptions.MessageError as exc:
self.msgbox.displayExc(exc)
problems = True
outList.append("")
break
## Output results
outputter = SpreadsheetOutput(self.unoObjs)
try:
outputter.outputToColumn(destCol, outList, skipFirstRow)
except exceptions.DocAccessError:
self.msgbox.display("Error writing to spreadsheet.")
progressBar.updateFinishing()
progressBar.close()
## Display results
if not problems:
if numDataChanges == 0:
self.msgbox.display("No changes.")
else:
self.msgbox.display("Successfully finished conversion.")
def doConversions_writer(self):
"""For converting data in a Writer doc."""
logger.debug(util.funcName('begin'))
## Start progress bar
progressBar = ProgressBar(self.unoObjs, "Converting...")
progressBar.show()
progressBar.updateBeginning()
## Find the text ranges
textSearch = TextSearch(self.unoObjs, progressBar)
textSearch.setConfig(self.config.searchConfig)
try:
if self.config.whichScope == 'WholeDoc':
textSearch.scopeWholeDoc()
elif self.config.whichScope == 'Selection':
textSearch.scopeSelection()
elif self.config.whichScope == 'ParaStyle':
textSearch.scopeParaStyle()
elif self.config.whichScope == 'CharStyle':
textSearch.scopeCharStyle()
elif self.config.whichScope == 'Font':
textSearch.scopeFont()
elif self.config.whichScope == 'SFMs':
textSearch.scopeSFMs()
else:
raise exceptions.LogicError("Unexpected value %s",
self.config.whichScope)
except (exceptions.RangeError, exceptions.LogicError) as exc:
self.msgbox.displayExc(exc)
progressBar.close()
return
rangesFound = textSearch.getRanges()
if progressBar.getPercent() < 40:
progressBar.updatePercent(40)
## Do the changes to those ranges
textChanger = TextChanger(self.unoObjs, progressBar,
self.changerSettings)
if self.secCall.config.convName:
textChanger.setConverterCall(self.secCall)
if self.config.whichTarget == "ParaStyle":
textChanger.setStyleToChange("ParaStyleName",
self.config.targetStyle)
elif self.config.whichTarget == "CharStyle":
textChanger.setStyleToChange("CharStyleName",
self.config.targetStyle)
elif self.config.whichTarget == "FontOnly":
textChanger.setFontToChange(self.config.targetFont)
numDataChanges, numStyleChanges = textChanger.doChanges(
rangesFound, self.config.askEach)
progressBar.updateFinishing()
progressBar.close()
## Display results
paragraphsFound = len(rangesFound)
if paragraphsFound == 0:
self.msgbox.display("Did not find scope of change.")
elif numDataChanges == 0:
if numStyleChanges == 0:
self.msgbox.display("No changes.")
else:
plural = "" if numStyleChanges == 1 else "s"
# add "s" if plural
self.msgbox.display(
"No changes, but modified style of %d paragraph%s.",
numStyleChanges, plural)
elif paragraphsFound == 1:
plural = "" if numDataChanges == 1 else "s" # add "s" if plural
self.msgbox.display("Made %d change%s.", numDataChanges, plural)
else:
plural = "" if numDataChanges == 1 else "s" # add "s" if plural
self.msgbox.display("Found %d paragraphs and made %d change%s.",
paragraphsFound, numDataChanges, plural)