How to use _findText method in fMBT

Best Python code snippet using fMBT_python

mets.py

Source:mets.py

1"""Code for parsing METS files."""2from __future__ import annotations3from collections import defaultdict4from dataclasses import dataclass5from typing import Dict, Iterable, List, Mapping, Optional6import requests7import shortuuid8from lxml import etree9#: Namespaces that are going to be used during XML parsing10NAMESPACES = {11    'mets': 'http://www.loc.gov/METS/',12    'mods': 'http://www.loc.gov/mods/v3',13    'dv': 'http://dfg-viewer.de/',14    'xlink': 'http://www.w3.org/1999/xlink'}15# Utility datatypes16@dataclass17class ImageInfo:18    """Metadata about an image."""19    id: str20    url: str21    mimetype: Optional[str] = None22    width: Optional[int] = None23    height: Optional[int] = None24@dataclass25class PhysicalItem:26    """A METS physical item (most often a page)."""27    ident: str28    label: str29    files: Iterable[ImageInfo]30    image_ident: Optional[str] = None31    @property32    def max_dimensions(self):33        """Maximum dimensions in pixels."""34        return max((f.width, f.height) for f in self.files)35    @property36    def min_dimensions(self):37        """Minimum dimensions in pixels."""38        return min((f.width, f.height) for f in self.files)39@dataclass40class TocEntry:41    """A table of contents entry."""42    children: List[TocEntry]  # pylint:disable=undefined-variable43    physical_ids: List[str]44    logical_id: str45    label: str46    type: str47class MetsParseError(Exception):48    """An exception that occured while parsing a METS file."""49    def __init__(self, message: str, debug_info: dict = None) -> None:50        super().__init__(message)51        self.debug_info = debug_info52class MetsDocument:53    """A parsed METS document.54    Note that this is not a generic METS parser, but currently highly coupled55    to both the METS/MODS profile required by the German 'DFG Viewer' and the56    later use as IIIF metadata (which is **not** intended to be57    machine-readable)58    """59    _tree: etree.ElementTree60    _mods_root: etree.Element61    identifiers: Dict[str, str]62    primary_id: str63    physical_items: Dict[str, PhysicalItem]64    toc_entries: Iterable[TocEntry]65    metadata: dict66    files: Dict[str, ImageInfo]67    def __init__(self, mets_tree: etree.ElementTree, url: str = None,68                 primary_id: str = None) -> None:69        """Parse a METS document.70        This will read the metadata, table of contents and general71        file informations. The width and heights of the images is72        not determined.73        """74        self.url = url75        self._tree = mets_tree76        self._mods_root = self._xpath("(.//mods:mods)[1]")[0]77        self.identifiers = {78            e.get('type'): e.text79            for e in self._xpath("./mods:identifier", self._mods_root)}80        recordid_elem = self._find(81            ".//mods:recordInfo/mods:recordIdentifier", self._mods_root)82        if recordid_elem is not None:83            key = recordid_elem.get('source')84            self.identifiers[key] = recordid_elem.text85        self.primary_id = primary_id or self._get_unique_identifier()86        self.metadata = self._read_metadata()87        self.files = self._read_files()88        if not self.files:89            raise MetsParseError(90                f"METS at {self.url} does not reference any JPEG images")91        self.physical_items = self._read_physical_items()92        self.toc_entries = self._read_toc_entries()93    def _xpath(self, xpath: str,94               elem: etree.Element = None) -> List[etree.Element]:95        elem = elem if elem is not None else self._tree96        return elem.xpath(xpath, namespaces=NAMESPACES)97    def _find(self, path: str, elem: etree.Element = None) -> etree.Element:98        elem = elem if elem is not None else self._tree99        return elem.find(path, namespaces=NAMESPACES)100    def _findall(self, path: str,101                 elem: etree.Element = None) -> List[etree.Element]:102        elem = elem if elem is not None else self._tree103        return elem.findall(path, namespaces=NAMESPACES)104    def _findtext(self, path: str, elem: etree.Element = None) -> str:105        elem = elem if elem is not None else self._tree106        return elem.findtext(path, namespaces=NAMESPACES)107    def _parse_title(self, title_elem: etree.Element) -> str:108        title = self._findtext(".//mods:title", title_elem)109        nonsort = self._findtext(".//mods:nonSort", title_elem)110        if nonsort:111            title = nonsort + title112        subtitle = self._findtext(".//mods:subTitle", title_elem)113        if subtitle:114            title = f"{title}. {subtitle}"115        return title116    def _parse_name(self, name_elem: etree.Element) -> str:117        name = self._findtext("./mods:displayForm", name_elem)118        if not name:119            name = " ".join(120                e.text for e in self._findall("./mods:namePart", name_elem))121        return name122    def _read_persons(self) -> Mapping[str, List[str]]:123        persons: Mapping[str, List[str]] = defaultdict(list)124        name_elems = self._xpath("./mods:name", self._mods_root)125        for e in name_elems:126            name = self._parse_name(e)127            role = self._findtext("./mods:role/mods:roleTerm", e)128            if role == 'aut':129                persons['creator'].append(name)130            else:131                persons['other_persons'].append(name)132        return persons133    def _read_origin(self) -> Mapping[str, str]:134        info_elem = self._find("./mods:originInfo", self._mods_root)135        return {136            'publisher': self._findtext("./mods:publisher", info_elem),137            'pub_place': self._findtext("./mods:place/mods:placeTerm",138                                        info_elem),139            'pub_date': self._findtext("./mods:dateIssued", info_elem)}140    def _get_unique_identifier(self) -> str:141        identifier = ''142        for type_ in ('oai', 'urn'):143            # Identifiers that are intended to be globally unique144            if identifier:145                break146            identifier = self._findtext(f"./mods:identifier[@type='{type_}']",147                                        self._mods_root)148        if not identifier:149            # MODS recordIdentifier, usually available on ZVDD documents150            identifier = self._findtext(151                "./mods:recordInfo/mods:recordIdentifier",152                self._mods_root)153        if not identifier:154            # Random identifier155            identifier = shortuuid.uuid()156        return identifier157    def _read_titles(self) -> List[str]:158        title_elems = self._findall("./mods:titleInfo", self._mods_root)159        if not title_elems:160            # For items with no title of their own that are part of a larger161            # multi-volume work162            title_elems = [self._findall(163                ".//mods:relatedItem[@type='host']/mods:titleInfo")[0]]164        # TODO: Use information from table of contents to find out about165        #       titles of multi-volume work166        titles = [self._parse_title(e) for e in title_elems]167        part_number = self._findtext(".//mods:part/mods:detail/mods:number")168        if part_number:169            titles = [f"{title} ({part_number})" for title in titles]170        return titles171    def _read_metadata(self) -> dict:172        metadata: dict = {}173        metadata.update(self._read_persons())174        metadata.update(self._read_origin())175        metadata['title'] = self._read_titles()176        owner_url = self._findtext(".//mets:rightsMD//dv:ownerSiteURL")177        owner = self._findtext(".//mets:rightsMD//dv:owner")178        if owner_url:179            metadata['attribution'] = (180                f"<a href='{owner_url}'>{owner or owner_url}</a>")181        elif owner:182            metadata['attribution'] = owner183        else:184            metadata['attribution'] = 'Unknown'185        metadata['logo'] = self._findtext(186            ".//mets:rightsMD//dv:ownerLogo")187        metadata['see_also'] = []188        if self.url:189            metadata['see_also'].append(190                [{'@id': self.url, 'format': 'text/xml',191                  'profile': 'http://www.loc.gov/METS/'}])192        pdf_url = self._xpath(193            ".//mets:fileGrp[@USE='DOWNLOAD']/"194            "mets:file[@MIMETYPE='application/pdf']/"195            "mets:FLocat/@xlink:href")196        if pdf_url and len(pdf_url) == 1:197            metadata['see_also'].append(198                {'@id': pdf_url, 'format': 'application/pdf'})199        metadata['related'] = self._findtext(200            ".//mets:digiprovMD//dv:presentation")201        license_ = self._findtext(".//dv:rights/dv:license")202        if not license_:203            license_ = self._findtext(".//mods:accessCondition")204        if not license_:205            license_ = 'reserved'206        metadata['license'] = license_207        # TODO: mods:physicalDescription208        metadata['language'] = self._findtext(209            ".//mods:languageTerm[@type='text']")210        metadata['genre'] = self._findtext(".//mods:genre")211        metadata['description'] = self._findtext(".//mods:abstract") or ""212        # TODO: Add mods:notes to description213        return metadata214    def _read_files(self) -> Dict[str, ImageInfo]:215        img_specs = (self._get_image_specs(e)216                     for e in self._findall(".//mets:file"))217        return {info.id: info for info in img_specs218                if info.url and info.url.startswith('http')219                and info.mimetype == 'image/jpeg'}220    def _read_physical_items(self) -> Dict[str, PhysicalItem]:221        """Create a map from physical IDs to (label, image_info) pairs."""222        if self.files is None:223            raise ValueError(224                "Can't read physical items before files have been read.")225        physical_items = {}226        pages = self._findall(227            ".//mets:structMap[@TYPE='PHYSICAL']"228            "/mets:div[@TYPE='physSequence']"229            "/mets:div[@TYPE='page']")230        for page_elem in sorted(pages, key=lambda e: int(e.get('ORDER'))):231            page_id = page_elem.get('ID')232            for label_attr in ('LABEL', 'ORDERLABEL', 'ORDER'):233                label = page_elem.get(label_attr)234                if label:235                    break236            if not label:237                label = '?'238            files = [239                self.files[ptr.get('FILEID')]240                for ptr in self._findall("./mets:fptr", page_elem)241                if ptr.get('FILEID') in self.files]242            physical_items[page_id] = PhysicalItem(243                page_id, label, [f for f in files if f is not None])244        return physical_items245    def _parse_tocentry(self, toc_elem: etree.Element,246                        lmap: Mapping[str, List[str]]) -> TocEntry:247        """Parse a toc entry subtree to a MetsTocEntry object."""248        log_id = toc_elem.get('ID')249        entry = TocEntry(250            children=[], physical_ids=lmap.get(log_id, []),251            type=toc_elem.get('TYPE'),252            logical_id=log_id, label=toc_elem.get('LABEL'))253        for e in self._findall("./mets:div", toc_elem):254            entry.children.append(self._parse_tocentry(e, lmap))255        return entry256    def _read_toc_entries(self) -> List[TocEntry]:257        """Create trees of TocEntries from the METS."""258        toc_entries = []259        lmap: Dict[str, List[str]] = {}260        mappings = [261            (e.get('{%s}from' % NAMESPACES['xlink']),262             e.get('{%s}to' % NAMESPACES['xlink']))263            for e in self._findall(".//mets:structLink//mets:smLink")]264        for logical_id, physical_id in mappings:265            if logical_id not in lmap:266                lmap[logical_id] = []267            lmap[logical_id].append(physical_id)268        for e in self._xpath(".//mets:structMap[@TYPE='LOGICAL']/mets:div"):269            toc_entries.append(self._parse_tocentry(e, lmap))270        return toc_entries271    def _get_image_specs(self, file_elem: etree.Element) -> ImageInfo:272        image_id = file_elem.get('ID')273        mimetype = file_elem.get('MIMETYPE').replace('jpg', 'jpeg')274        location = self._xpath(275            "./mets:FLocat[@LOCTYPE='URL']/@xlink:href", file_elem)276        return ImageInfo(image_id, location[0] if location else None, mimetype)277def get_basic_info(mets_url):278    from .iiif import make_label279    xml = requests.get(mets_url, allow_redirects=True).content280    tree = etree.fromstring(xml)281    doc = MetsDocument(tree, url=mets_url)282    thumb_urls = doc._xpath(283        ".//mets:file[@MIMETYPE='image/jpeg']/mets:FLocat/@xlink:href")284    if not thumb_urls:285        thumb_urls = doc._xpath(286            ".//mets:file[@MIMETYPE='image/jpg']/mets:FLocat/@xlink:href")287    return {288        'metsurl': mets_url,289        'label': make_label(doc.metadata),290        'thumbnail': thumb_urls[0] if thumb_urls else None,291        'attribution': {292            'logo': doc.metadata['logo'],293            'owner': doc.metadata['attribution']294        }...

SourceViewDialog.py

Source:SourceViewDialog.py

1__version__ = "$Id$"2import ViewDialog3import windowinterface, usercmd4from usercmd import *5import features6class SourceViewDialog(ViewDialog.ViewDialog):7    readonly = features.SOURCE_VIEW_EDIT not in features.feature_set8    def __init__(self):9        ViewDialog.ViewDialog.__init__(self, 'sourceview_')10        self.__textwindow = None11        self.__setCommonCommandList()12        self._findReplaceDlg = None13        self._findText = ''14        self._replaceText = None15        self._findOptions = (0,0)16        self.__selChanged = 117        self.__replacing = 018    def __setCommonCommandList(self):19        self._commonCommandList = [SELECTNODE_FROM_SOURCE(callback = (self.onRetrieveNode, ())),20                                   FIND(callback = (self.onFind, ())),21                                   FINDNEXT(callback = (self.onFindNext, ())),22                                   ]23        self._copyCommand = [COPY(callback = (self.onCopy, ()))]24        if self.readonly:25            self._undoCommand = []26            self._cutCommand = []27            self._pasteComamnd = []28        else:29            self._commonCommandList.append(REPLACE(callback = (self.onReplace, ())))30            self._undoCommand = [UNDO(callback = (self.onUndo, ()))]31            self._copyCommand.append(CUT(callback = (self.onCut, ())))32            self._pasteComamnd = [PASTE(callback = (self.onPaste, ()))]33    def destroy(self):34        self.__textwindow = None35    def show(self):36        self.load_geometry()37        if not self.__textwindow:38            import MenuTemplate39            self.window = self.__textwindow = \40                    self.toplevel.window.textwindow("", readonly=self.readonly, xywh=self.last_geometry, title='Source')41            self.__textwindow.set_mother(self)42            self.setpopup(MenuTemplate.POPUP_SOURCEVIEW)43        else:44            # Pop it up45            self.pop()46        self.__updateCommandList()47        self.__textwindow.setListener(self)48    def get_geometry(self):49        if self.__textwindow:50            self.last_geometry = self.__textwindow.getgeometry(windowinterface.UNIT_PXL)51            return self.last_geometry52    def pop(self):53        if self.__textwindow != None:54            self.__textwindow.pop()55    def __updateCommandList(self):56        commandList = []57        # undo58        if not self.readonly and self.__textwindow.canUndo():59            commandList.append(UNDO(callback = (self.onUndo, ())))60        # copy/paste/cut61        if self.__textwindow.isSelected():62            commandList = commandList + self._copyCommand63        if not self.readonly and not self.__textwindow.isClipboardEmpty():64            commandList = commandList + self._pasteComamnd65        # other operations all the time actived66        commandList = commandList+self._commonCommandList67        self.setcommandlist(commandList)68    def is_showing(self):69        if self.__textwindow:70            return 171        else:72            return 073    def hide(self):74        self.save_geometry()75        if self.__textwindow:76            self.__textwindow.removeListener()77            self.__textwindow.close()78            self.__textwindow = None79        if self._findReplaceDlg:80            self._findReplaceDlg.hide()81            self._findReplaceDlg = None82    def setcommandlist(self, commandlist):83        if self.__textwindow:84            self.__textwindow.set_commandlist(commandlist)85    def setpopup(self, template):86        if self.__textwindow:87            self.__textwindow.setpopupmenu(template)88    def get_text(self):89        if self.__textwindow:90            return self.__textwindow.gettext()91        else:92            print "ERROR (get_text): No text window."93    def set_text(self, text, colors=[]):94        if self.__textwindow:95            return self.__textwindow.settext(text, colors)96        else:97            print "ERROR (set text): No text window"98    def is_changed(self):99        if self.readonly:100            return 0101        if self.__textwindow:102            return self.__textwindow.isChanged()103    def select_chars(self, s, e):104        if self.__textwindow:105            self.__textwindow.select_chars(s,e)106    def select_lines(self, sLine, eLine):107        if self.__textwindow:108            self.__textwindow.select_line(sLine)109    # return the current line pointed by the carret110    def getCurrentCharIndex(self):111        if self.__textwindow:112            return self.__textwindow.getCurrentCharIndex()113        return -1114    # return the line number115    def getLineNumber(self):116        if self.__textwindow:117            return self.__textwindow.getLineNumber()118        return 0119    #120    # text window listener interface121    #122    # this call back is called when the selection change123    def onSelChanged(self):124        self.__updateCommandList()125        self.__selChanged = 1126        if not self.__replacing and self._findReplaceDlg != None:127            self._findReplaceDlg.enableReplace(0)128    # this call back is called when the content of the clipboard change (or may have changed)129    def onClipboardChanged(self):130        self.__updateCommandList()131    #132    # command listener interface133    #134    # note: these copy, paste and cut operation don't use the GRiNS clipboard135    def onCopy(self):136        self.__textwindow.Copy()137    def onCut(self):138        if self.readonly:139            self.__textwindow.Copy()140        else:141            self.__textwindow.Cut()142    def onPaste(self):143        if not self.readonly:144            self.__textwindow.Paste()145    def onUndo(self):146        if not self.readonly:147            self.__textwindow.Undo()148    #149    # find/replace support150    #151    def onFind(self):152        # if another dlg was showed, we hide it153        if self._findReplaceDlg != None:154            self._findReplaceDlg.hide()155            self._findReplaceDlg = None156        import win32dialog157        self._findReplaceDlg = win32dialog.FindDialog(self.doFindNext, self._findText, self._findOptions, self.window)158        self._findReplaceDlg.show()159    def onFindNext(self):160        if self._findText != None:161            self.doFindNext(self._findText, self._findOptions)162    def onReplace(self):163        if self.readonly:164            return165        # if another dlg was shown, we hide it166        if self._findReplaceDlg != None:167            self._findReplaceDlg.hide()168            self._findReplaceDlg = None169        import win32dialog170        self._findReplaceDlg = win32dialog.ReplaceDialog(self.doFindNext, self.doReplace, self.doReplaceAll, \171                                                                                                        self._findText, self._replaceText, self._findOptions, self.window)172        self._findReplaceDlg.show()173        if not self.__selChanged:174            self._findReplaceDlg.enableReplace(1)175    def doFindNext(self, text, options):176        if not self.__textwindow:177            return178        # save the text and options for the next time179        self._findText = text180        self._findOptions = options181        found = 0182        # first search from the current position183        begin = self.getCurrentCharIndex()184        if self.__textwindow.findNext(begin, text, options) == None:185            # not found, search from the begining186            ret = self.__textwindow.findNext(0, text, options)187            if ret == None:188                windowinterface.showmessage("No more occurrences.", mtype = 'error')189            else:190                found = 1191        else:192            found = 1193        if self._findReplaceDlg != None:194            self._findReplaceDlg.enableReplace(found)195        # raz the flag whitch allows to know if a replace if directly possible.196        self.__selChanged = 0197    def doReplace(self, text, options, replaceText):198        if self.readonly or not self.__textwindow:199            return200        # save the text and options for the next time201        self._findOptions = options202        if self._findText != text:203            # the findwhat value has changed since the last find204            # in this special case, we jump to the next value without automatic replace205            self._findText = text206            self.onFindNext()207            return208        self.__replacing = 1209        # save the text and options for the next time210        self._findText = text211        # save the text for the next time212        self._replaceText = replaceText213        if self.__textwindow:214            self.__textwindow.replaceSel(replaceText)215            # seek on the next occurrence found216            self.onFindNext()217        self.__replacing = 0218    def doReplaceAll(self, text, options, replaceText):219        if self.readonly or not self.__textwindow:220            return221        self.__replacing = 1222        # save the text and options for the next time223        self._findText = text224        self._findOptions = options225        begin = 0226        nocc = 0227        lastPos = None228        pos = self.__textwindow.findNext(begin, self._findText, self._findOptions)229        while pos != None and lastPos != pos:230            lastPos = pos231            self.__textwindow.replaceSel(replaceText)232            begin = self.getCurrentCharIndex()233            nocc = nocc + 1234            pos = self.__textwindow.findNext(begin, self._findText, self._findOptions)235        self.__replacing = 0...

ResultsReader.py

Source:ResultsReader.py

...16    for s in map(_ns, path):17        xpath += s + '/'18    xpath = xpath.rstrip('/')19    return xpath20def _findText(root, xpath) -> str:21    try:22        return root.find(xpath).text23    except AttributeError:24        return None25def _findNodes(root, xpath):26    try:27        return root.findall(xpath)28    except AttributeError:29        return None30class ResultListReader:31    def __init__(self, file:SpooledTemporaryFile):32        self.file = file33        with self.file as f:34            tree = parse(f)35            root = tree.getroot()36            if root.tag != _ns('ResultList'):37                raise TypeError(f'{root.tag} is not an ResultList')38            self.root = root39        self.race_name = _findText(self.root, _nspath(["Event", "Name"]))40        self.class_results = _findNodes(self.root, _nspath(["ClassResult"]))41class ClassResultReader:42    def __init__(self, el):43        if el.tag != _ns('ClassResult'):44            raise TypeError(f'{el.tag} is not a ClassResult')45        self.root = el46        self.class_name = _findText(self.root, _nspath(["Class", "Name"]))47        self.class_name_short = _findText(self.root, _nspath(["Class", "ShortName"]))48        self.course_name = _findText(self.root, _nspath(["Course", "Name"]))49        self.course_id = _findText(self.root, _nspath(["Course", "Id"]))50        self.course_length = _findText(self.root, _nspath(["Course", "Length"]))51        self.course_climb = _findText(self.root, _nspath(["Course", "Climb"]))52        self.course_controls = _findText(self.root, _nspath(["Course", "NumberOfControls"]))53        self.result_nodes = _findNodes(self.root, _nspath(["PersonResult"]))54class PersonResultReader:55    def __init__(self, el):56        if el.tag != _ns('PersonResult'):57            raise TypeError(f'{el.tag} is not a PersonResult')58        self.root = el59        self.first_name = _findText(self.root, _nspath(["Person", "Name", "Given"]))60        self.last_name = _findText(self.root, _nspath(["Person", "Name", "Family"]))61        self.bib = _findText(self.root, _nspath(["Result", "BibNumber"]))62        self.start_time = _findText(self.root, _nspath(["Result", "StartTime"]))63        if self.start_time is not None:64            try:65                self.start_time = datetime.strptime(self.start_time, TIMEFORMAT)66            except ValueError:67                self.start_time = datetime.strptime(self.start_time[:-6], TIMEFORMAT)68        self.finish_time = _findText(self.root, _nspath(["Result", "FinishTime"]))69        if self.finish_time is not None:70            try:71                self.finish_time = datetime.strptime(self.finish_time, TIMEFORMAT)72            except ValueError:73                self.finish_time = datetime.strptime(self.finish_time[:-6], TIMEFORMAT)74        self.time = _findText(self.root, _nspath(["Result", "Time"]))75        self.status = _findText(self.root, _nspath(["Result", "Status"]))76        self.control_card = _findText(self.root, _nspath(["Result", "ControlCard"]))77        self.club_name = _findText(self.root, _nspath(["Organisation", "Name"]))78        if self.club_name == 'None':79            self.club_name = None80        self.club_name_short = _findText(self.root, _nspath(["Organisation", "ShortName"]))81        if self.club_name_short == 'None':...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.