tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/rtf/TextExtractor.java (14 lines):
	- line 59: * TODO: we should cutover to a "real" tokenizer (eg JFlex);
	- line 236: // TODO: in theory these other charsets are simple
	- line 326: //TODO:
	- line 539: // TODO: log a warning here, somehow?
	- line 852: // TODO: afN?  (associated font number)
	- line 854: // TODO: do these alter text output...?
	- line 873: // TODO: inefficient that we check equals N times;
	- line 984: // TODO: log a warning?  Throw an exc?
	- line 1123: // TODO: we can also parse \creatim, \revtim,
	- line 1255: // TODO: we should produce a table output here?
	- line 1275: // TODO: create img tag?  but can that support
	- line 1488: // TODO: log a warning?
	- line 1527: // TODO: what other instructions can be in a
	- line 1543: // TODO: we could process the other known field


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/tools/SlowCompositeReaderWrapper.java (13 lines):
	- line 77: // TODO: consider ConcurrentHashMap ?
	- line 78: // TODO: this could really be a weak map somewhere else on the coreCacheKey,
	- line 145: // TODO: this is trappy as the expectation is that core keys live for a long
	- line 175: return MultiDocValues.getNumericValues(in, field); // TODO cache?
	- line 181: return MultiDocValues.getBinaryValues(in, field); // TODO cache?
	- line 187: return MultiDocValues.getSortedNumericValues(in, field); // TODO cache?
	- line 291: return MultiDocValues.getNormValues(in, field); // TODO cache?
	- line 296: //TODO figure out how to implement this... if needed
	- line 302: //TODO figure out how to implement this... if needed
	- line 308: //TODO figure out how to implement this... if needed
	- line 313: //TODO figure out how to implement this... if needed
	- line 357: return MultiBits.getLiveDocs(in); // TODO cache?
	- line 373: // TODO: as this is a wrapper, should we really close the delegate?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java (13 lines):
	- line 77: COMMON_TAG_MAP.put("td", new HtmlTag("td"));//TODO -- convert to th if in thead?
	- line 199: //TODO: is there a better way of getting these/doing the mapping?
	- line 239: //TODO: LOG! piece of text that wasn't referenced  in the marked content
	- line 254: //TODO: figure out when we're crossing page boundaries during the recursion
	- line 279: //TODO should be merged with COSDictionary segment below?
	- line 316: //TODO: currently suppressing span and lbody...
	- line 355: //TODO: log can't find mcid
	- line 358: //TODO: check for other types of dictionary?
	- line 375: //TODO: handle a different object?
	- line 426: //TODO: at some point also handle
	- line 434: //TODO: sort text positions? Figure out when to add/remove a newline and/or space?
	- line 443: TODO: do we want to do anything with these?
	- line 444: TODO: Are there other types of objects we need to handle here?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/image/ImageGraphicsEngine.java (10 lines):
	- line 102: //TODO: parameterize this ?
	- line 105: //TODO: this is an embarrassment of an initializer...fix
	- line 174: //TODO: log or otherwise report
	- line 233: //TODO: is there a better way to do this rather than reprocessing the page
	- line 273: //TODO: handle image metadata: xobject.getMetadata()
	- line 286: //TODO: should we use the hash of the PDImage to check for seen
	- line 405: //TODO -- should we look for image rotation metadata in the PDImage or elsewhere?
	- line 449: //TODO: what else can we extract from the PDImage without rendering?
	- line 482: //TODO: determine if we need to add more image types
	- line 496: //TODO -- is there a cleaner way of checking for:


tika-core/src/main/java/org/apache/tika/config/TikaConfigSerializer.java (9 lines):
	- line 111: // TODO Service Loader section
	- line 128: // TODO Implement the reverse of ExecutorServiceXmlLoader
	- line 129: // TODO Make it possible to detect if we have the default executor
	- line 130: // TODO Make it possible to get the current values from ConfigurableThreadPoolExecutor
	- line 298: // TODO Parser Exclusions
	- line 346: //TODO -- check code base for setters with lowercase initial letters?!
	- line 366: //TODO -- check code base for setX() zero parameters that set boolean to true
	- line 391: //TODO -- remove nonprimitive setters/getters that have a string equivalent
	- line 566: //TODO -- if both string and integer, which one do we pick?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java (9 lines):
	- line 165: * TODO Make this thread-safe
	- line 455: // TODO: other metadata?
	- line 579: //TODO: we need to prevent this if only a portion of the page or portions
	- line 581: //TODO: we should also figure out how to not reuse the rendering if
	- line 673: //TODO -- get suffix based on OcrImageType
	- line 676: //TODO: get output format from TesseractConfig
	- line 744: // TODO: remove once PDFBOX-1143 is fixed:
	- line 763: // TODO: maybe also annotationMarkup.getRichContents()?
	- line 1077: //TODO figure out better way of managing this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLWordAndPowerPointTextHandler.java (8 lines):
	- line 47: * TODO: move this into POI?
	- line 119: //in run or in field. TODO: convert this to an integer because you can have a run within a run
	- line 184: //TODO: checkBox, textBox, sym, headerReference, footerReference, commentRangeEnd
	- line 221: } else if (B.equals(localName)) { //TODO: add bCs
	- line 230: } else if (I.equals(localName)) { //TODO: add iCs
	- line 293: } //TODO: add sdt, sdtPr, sdtContent goes here statistically
	- line 313: //TODO: clean this up and ...want to get ProgID?
	- line 406: //a run...TODO: should we swallow whitespace that doesn't occur in a run?


tika-core/src/main/java/org/apache/tika/language/detect/LanguageNames.java (8 lines):
	- line 27: * TODO change to LanguageTag, and use these vs. strings everywhere in the
	- line 46: // TODO make it so.
	- line 52: // TODO make it so
	- line 65: // TODO make it so
	- line 73: // TODO Fill in script if missing and something we could derive from lang+region
	- line 76: // TODO Treat missing script == present script, if present script is default
	- line 79: // TODO probably OK to ignore extensions
	- line 81: // TODO Do we want/need a fuzzy match for region (and script)


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParser.java (7 lines):
	- line 299: //TODO -- can we use the PDFBox parser's RandomAccessRead
	- line 312: //TODO figure out better way of managing this
	- line 361: //TODO -- consider parsing the metadata
	- line 408: //TODO: test that this is not AUTO with no OCR parser installed
	- line 516: //TODO: are there other checks we need to perform?
	- line 649: //TODO: Let's try to move this into PDFBox.
	- line 1123: //TODO -- figure out how to deserialize this in TikaConfigSerializer


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetRecog_mbcs.java (6 lines):
	- line 49: @SuppressWarnings("unused") int singleByteCharCount = 0;  //TODO Do we really need this?
	- line 185: // TODO:  This set of data comes from the character frequency-
	- line 243: // TODO:  This set of data comes from the character frequency-
	- line 376: // TODO:  This set of data comes from the character frequency-
	- line 411: // TODO:  This set of data comes from the character frequency-
	- line 447: // TODO:  This set of data comes from the character frequency-


tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml (5 lines):
	- line 3210: <!-- TODO: figure out how to identify earlier versions -->
	- line 3236: <!--TODO: figure out how to distinguish 6.x versions -->
	- line 4871: TODO: add detection for wb2 and wb1 -->
	- line 5659: <!-- TODO: Add matches for the other possible XML encoding schemes -->
	- line 7418: <!-- TODO See TIKA-2723 for discussions on the mime type hierarchy -->


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java (5 lines):
	- line 219: // TODO Fetch the array values and output
	- line 221: // TODO Fetch the vector values and output
	- line 223: // TODO Decode, if possible
	- line 226: // TODO Decode, if possible
	- line 228: // TODO Decode, if possible


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNotePtr.java (5 lines):
	- line 343: // TODO check that next is OK
	- line 544: // FIXME: deal with ObjectDataEncryptionKey
	- line 648: // TODO - call postprocessObjectDeclarationContents on this object?
	- line 766: // TODO - the expected header is different per version of one note.
	- line 788: // TODO - the expected footer is per version of one note.


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java (5 lines):
	- line 49: * TODO: integrate table markup
	- line 365: // TODO: Implement splitting for RTL too
	- line 479: // TODO: This could be optimised using a binary search since we know rows is sorted
	- line 500: //TODO: use name in conjunction with Frag information
	- line 573: // TODO: Parse other elements of GlyphIndex


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/renderer/pdf/mutool/MuPDFRenderer.java (5 lines):
	- line 86: //TODO -- this assumes files have been deleted first
	- line 94: //TODO -- run mutool pages to get page sizes
	- line 102: //TODO: parameterize timeout
	- line 107: //TODO -- fix this
	- line 126: //TODO parameterize all the things; mutool path, colorspace and size and format and...


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java (5 lines):
	- line 86: //TODO: take into consideration the filename.  Perhaps require
	- line 168: //TODO: test to make sure cell doesn't start with escaped
	- line 345: //TODO -- do some analysis to make sure you don't have
	- line 355: //TODO -- add tests for long tokens containing
	- line 397: //TODO: convert this to continuous vs vague heuristic step function


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetRecog_sbcs.java (5 lines):
	- line 145: // TODO: 0x20 might not be a space in all character sets...
	- line 167: // TODO: Is this OK? The buffer could have ended in the middle of a word...
	- line 176: // TODO - This is a bit of a hack to take care of a case
	- line 290: // TODO: 0x20 might not be a space in all character sets...
	- line 301: // TODO: 0x20 might not be a space in all character sets...


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java (4 lines):
	- line 71: //TODO: what else
	- line 231: //TODO: consider: getPackage().getPartsByName(Pattern.compile("/ppt/embeddings/.*?
	- line 232: //TODO: consider: getPackage().getPartsByName(Pattern.compile("/ppt/media/.*?
	- line 387: //TODO: require that we're in <p:text>?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/TextAndCSVParser.java (4 lines):
	- line 176: //TODO -- if it was detected as a non-csv subtype of text
	- line 216: //TODO -- figure out how to improve this
	- line 222: //TODO -- consider dumping what's left in the reader as text
	- line 332: //TODO: log bad/unrecognized delimiter string


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/warc/WARCParser.java (4 lines):
	- line 87: //TODO: record warnings in metadata: warcreader.onWarning();
	- line 115: //TODO - other warc record types
	- line 130: //TODO handle missing payload?  Report or ignore?
	- line 147: //TODO check Content-Encoding on the warcResponse.http.headers and wrap the stream.


tika-core/src/main/java/org/apache/tika/sax/SafeContentHandler.java (4 lines):
	- line 170: // TODO: enable this, but some parsers currently
	- line 198: // TODO: enable this, but some parsers currently
	- line 210: // TODO: we could strengthen this to do full
	- line 242: // TODO: enable this, but some parsers currently


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/fsshttpb/unsigned/UInteger.java (4 lines):
	- line 137: // FIXME: should we log this somewhere?
	- line 145: // FIXME: should we log this somewhere?
	- line 154: // FIXME: should we log this somewhere?
	- line 163: // FIXME: should we log this somewhere?


tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerConfig.java (3 lines):
	- line 86: TODO: integrate these settings:
	- line 109: //TODO: make parameterizable for debugging
	- line 580: //TODO fix this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java (3 lines):
	- line 166: //TODO: figure out if we can send in the PDPage in the TikaInputStream
	- line 178: //TODO: add markup here?
	- line 197: //TODO: modernize to ImageStratey != rawImages


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteLegacyDumpStrings.java (3 lines):
	- line 41: // TODO - parameterize this
	- line 43: // TODO - parameterize this
	- line 45: // TODO - parameterize this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-code-module/src/main/java/org/apache/tika/parser/sas/SAS7BDATParser.java (3 lines):
	- line 83: // TODO Can we find more general properties for these / move
	- line 105: // TODO Find keys to record the format and the type
	- line 135: //TODO: initialize this on the first row and then apply


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dbf/DBFCell.java (3 lines):
	- line 63: //TODO: find examples of other cell types for testing
	- line 127: //TODO: add heuristic for deciding;
	- line 128: //TODO: find example of file with time != 0


tika-core/src/main/java/org/apache/tika/pipes/PipesServer.java (3 lines):
	- line 326: //TODO: implement this
	- line 582: //TODO: especially clean this up.
	- line 763: //TODO allowed named configurations in tika config


tika-detectors/tika-detector-magika/src/main/java/org/apache/tika/detect/magika/MagikaDetector.java (3 lines):
	- line 80: //TODO -- grab errors and warnings
	- line 232: //TODO -- should we get values in "dl" instead or in addition?
	- line 257: //TODO -- should we get values in "dl" instead or in addition?


tika-serialization/src/main/java/org/apache/tika/serialization/TikaJsonDeserializer.java (3 lines):
	- line 214: //TODO this should try to match the map setters with the data types
	- line 243: //TODO -- maybe check for string?
	- line 394: //TODO -- check for over/underflow


tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/isatab/ISArchiveParser.java (3 lines):
	- line 110: // TODO warning
	- line 114: // TODO warning
	- line 118: String investigation = investigationList[0]; // TODO add to metadata?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/PSDParser.java (3 lines):
	- line 100: // TODO Identify a suitable metadata key for this
	- line 141: // TODO Parse the EXIF info via ImageMetadataExtractor
	- line 143: // TODO Parse the EXIF info via ImageMetadataExtractor


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/JempboxExtractor.java (3 lines):
	- line 47: //TODO: change signature to require parsecontext from parse
	- line 93: // TODO should we set SUBJECT too?
	- line 153: //TODO: not yet supported by XMPBox...extract OriginalDocumentID


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java (3 lines):
	- line 981: //TODO -- figure out if this is actual BEST or whatever
	- line 1000: //TODO: add AUTO?
	- line 1052: //TODO: add LOGICAL_IMAGES


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mail/MailContentHandler.java (3 lines):
	- line 77: //TODO -- specific handling for other multipart subtypes?  mixed, parallel, digest
	- line 454: // TODO Auto-generated method stub
	- line 569: //TODO -- is this the right definition in rfc822 for rich text?!


tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TikaServerProcess.java (3 lines):
	- line 205: //TODO -- clean this up -- only load as necessary
	- line 214: //TODO -- figure out how to turn this back on
	- line 309: //TODO figure out which ones to turn off


tika-core/src/main/java/org/apache/tika/parser/multiple/AbstractMultipleParser.java (3 lines):
	- line 103: // TODO Only offer those in common to several/all parser
	- line 104: // TODO Some sort of specialisation / subtype support
	- line 250: * TODO Do we need to return all the ContentHandler instances we created?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java (2 lines):
	- line 309: //TODO check for targetMode=INTERNAL?
	- line 487: //TODO -- should we record the literal name of the embedded file?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java (2 lines):
	- line 439: // TODO: identify bullet/list type
	- line 576: //TODO -- inject progId into the metadata of the embedded file


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/main/java/org/apache/tika/parser/iptc/IptcAnpaParser.java (2 lines):
	- line 105: // TODO: put body content here
	- line 294: // TODO: this only pulls back 8K of data on a read, regardless of buffer size


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java (2 lines):
	- line 316: // TODO: replace w/ XPath/XQuery:
	- line 343: //TODO: get ProgID, while we're here?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractListManager.java (2 lines):
	- line 136: //TODO: add in character after number
	- line 164: //not yet handled by NumberFormatter...TODO: add to NumberFormatter?


tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/captioning/tf/TensorflowRESTCaptioner.java (2 lines):
	- line 128: //TODO -- what do we want to check?
	- line 141: //TODO: convert this to stream, this might cause OOM issue


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xwpf/XWPFEventBasedWordExtractor.java (2 lines):
	- line 55: //TODO: move this into POI?
	- line 165: //TODO: XWPFStyles styles = loadStyles(documentPart);


tika-pipes/tika-fetchers/tika-fetcher-gcs/src/main/java/org/apache/tika/pipes/fetcher/gcs/GCSFetcher.java (2 lines):
	- line 124: //TODO: parameterize extracting other blob metadata, eg. md5, crc, etc.
	- line 135: //TODO -- add other params to the builder as needed


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/wordperfect/WP6Charsets.java (2 lines):
	- line 313: {  //TODO implement Current Font Symbols
	- line 387: //TODO map multi-characters


tika-pipes/tika-pipes-iterators/tika-pipes-iterator-az-blob/src/main/java/org/apache/tika/pipes/pipesiterator/azblob/AZBlobPipesIterator.java (2 lines):
	- line 124: //TODO -- extract metadata about content length etc from properties
	- line 137: //TODO -- allow authentication via other methods


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/BPGParser.java (2 lines):
	- line 86: // TODO Identify a suitable metadata key for this
	- line 90: // TODO Identify a suitable metadata key for this+hasAlphaPlane2


tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/tf/TensorflowRESTRecogniser.java (2 lines):
	- line 129: //TODO -- what do we want to check?
	- line 142: //TODO: convert this to stream, this might cause OOM issue


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/updates/StartXRefScanner.java (2 lines):
	- line 81: //TODO: if we're opening a new file for the source
	- line 120: //TODO -- make this more robust


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/audio/MidiParser.java (2 lines):
	- line 77: // TODO: Use XMPDM.TRACKS?
	- line 103: // FIXME: What's the encoding?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp4/MP4Parser.java (2 lines):
	- line 112: //TODO -- figure out how to get IOExceptions out of boxhandler. Mp4Reader
	- line 234: //TODO Replace this with a 2dp Duration Property Converter


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java (2 lines):
	- line 480: //TODO -- would be good to find an example triggering file and
	- line 734: // TODO: do we need to replicate this in Tika? If we wind up


tika-example/src/main/java/org/apache/tika/example/PickBestTextEncodingParser.java (2 lines):
	- line 54: * TODO Implement proper "Junk" detection
	- line 106: // TODO Do this in a more generic, less english-only way!


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java (2 lines):
	- line 137: // TODO Add support for the remaining CompressorInputStream formats:
	- line 154: // TODO Add unit tests for this format


tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java (2 lines):
	- line 223: //TODO: figure out safe way to shutdown resource crawler
	- line 521: //TODO: get rid of this?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java (2 lines):
	- line 274: //TODO: figure out if the equivalent of OLE 1.0's
	- line 330: //TODO: modify getEntry to case insensitive when available in POI


tika-pipes/tika-emitters/tika-emitter-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitter.java (2 lines):
	- line 89: //TODO: estimate size of metadata list.  Above a certain size,
	- line 250: //TODO -- allow authentication via other methods


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/ByteFlipper.java (2 lines):
	- line 34: //TODO add something about protecting first x bytes?
	- line 45: //TODO -- don't load the full thing into memory


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java (2 lines):
	- line 194: //TODO: add check for targetmode=external into POI
	- line 268: //TODO: Need to wait for fix in POI to test for hyperlink first


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/main/java/org/apache/tika/detect/zip/DeprecatedZipContainerDetector.java (2 lines):
	- line 19: //see TODO then delete this class
	- line 31: TODO: move this to the apple module


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java (2 lines):
	- line 93: //TODO PDFBOX30 replace COSWriterXRefEntry with XReferenceEntry (and much more)
	- line 636: //TODO: parameterize wonkifying length and filters


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPPacketScanner.java (2 lines):
	- line 101: //TODO Inspect "begin" attribute!
	- line 105: //TODO Do with TeeInputStream when Commons IO 1.4 is available


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/ExtractComparer.java (2 lines):
	- line 237: //TODO: shouldn't be fileA!!!!
	- line 396: //TODO: could make this more robust


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java (2 lines):
	- line 271: //TODO: consider getting parsing "Format" field from
	- line 323: //TODO: find test file that has this kind of attachment


tika-core/src/main/java/org/apache/tika/sax/xpath/MatchingContentHandler.java (2 lines):
	- line 91: // TODO: Support for matching processing instructions
	- line 95: // TODO: Can skipped entities refer to more than text?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WMFParser.java (2 lines):
	- line 73: //TODO: make x/y info public in POI so that we can use it here
	- line 77: //TODO: do what Graphics does by maintaining the stack, etc.!


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/odf/OpenDocumentBodyHandler.java (2 lines):
	- line 113: /* TODO: The following is not correct, the cell should be repeated not spanned!
	- line 517: //TODO: figure out whether we're in an inline image or a regular


tika-core/src/main/java/org/apache/tika/config/TikaConfig.java (2 lines):
	- line 738: //TODO : allow duplicate instances with different configurations
	- line 797: // TODO Support arguments, needed for Translators etc


tika-pipes/tika-pipes-iterators/tika-pipes-iterator-gcs/src/main/java/org/apache/tika/pipes/pipesiterator/gcs/GCSPipesIterator.java (2 lines):
	- line 78: //TODO -- add other params to the builder as needed
	- line 116: //TODO -- allow user specified metadata as the "id"?


tika-pipes/tika-emitters/tika-emitter-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitter.java (2 lines):
	- line 271: //TODO -- add other httpclient configurations??
	- line 313: //TODO -- there's more that we need to pass through, including ssl etc.


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dif/DIFParser.java (2 lines):
	- line 50: // TODO Auto-generated method stub
	- line 57: // TODO Auto-generated method stub


tika-core/src/main/java/org/apache/tika/extractor/RUnpackExtractor.java (2 lines):
	- line 114: //TODO -- improve the efficiency of this so that we're not
	- line 166: //TODO fix this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ImageMetadataExtractor.java (2 lines):
	- line 79: //TODO: add this to the signatures from the actual parse
	- line 552: //TODO: should we try to process ExifSubIFDDirectory.TAG_TIME_ZONE_OFFSET


tika-pipes/tika-pipes-iterators/tika-pipes-iterator-solr/src/main/java/org/apache/tika/pipes/pipesiterator/solr/SolrPipesIterator.java (2 lines):
	- line 149: //TODO -- add other httpclient configurations??
	- line 238: //TODO -- there's more that we need to pass through, including ssl etc.


tika-parsers/tika-parsers-ml/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ctakes/CTAKESConfig.java (2 lines):
	- line 97: // TODO warning
	- line 102: // TODO warning


tika-batch/src/main/java/org/apache/tika/batch/builders/BatchProcessBuilder.java (2 lines):
	- line 131: * TODO: This is a bit smelly.  NumConsumers needs to be used by the crawler
	- line 227: //TODO: should we have a max range check?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/main/java/org/apache/tika/detect/zip/DeprecatedStreamingZipContainerDetector.java (2 lines):
	- line 82: //odt -- TODO -- check that the results are valid
	- line 94: //TODO: do something if the full stream hasn't been read?


tika-langdetect/tika-langdetect-optimaize/src/main/java/org/apache/tika/langdetect/optimaize/OptimaizeLangDetector.java (2 lines):
	- line 138: // TODO what happens if you request a language that has no profile?
	- line 205: // TODO figure out right level for confidence brackets.


tika-pipes/tika-fetchers/tika-fetcher-az-blob/src/main/java/org/apache/tika/pipes/fetcher/azblob/AZBlobFetcher.java (1 line):
	- line 183: //TODO -- allow authentication via other methods


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-commons/src/main/java/org/apache/tika/parser/mailcommons/MailUtil.java (1 line):
	- line 90: //TODO: warn if more than one email is found?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmCommons.java (1 line):
	- line 72: // TODO add int_max_value checking


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/main/java/org/apache/tika/parser/prt/PRTParser.java (1 line):
	- line 93: // TODO Metadata.DATE is used as modified, should it be here?


tika-langdetect/tika-langdetect-opennlp/src/main/java/org/apache/tika/langdetect/opennlp/ProbingLanguageDetector.java (1 line):
	- line 169: // TODO -- once OPENNLP-1261 is fixed,


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/db/MimeBuffer.java (1 line):
	- line 75: //TODO: see if MimeType now works for these


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/wordperfect/WP5DocumentAreaExtractor.java (1 line):
	- line 108: //TODO Are there functions containing data? Like footnotes?


tika-pipes/tika-emitters/tika-emitter-opensearch/src/main/java/org/apache/tika/pipes/emitter/opensearch/OpenSearchEmitter.java (1 line):
	- line 164: //TODO -- add other httpclient configurations??


tika-example/src/main/java/org/apache/tika/example/Language.java (1 line):
	- line 40: // TODO support version of LanguageWriter that doesn't need a detector.


tika-core/src/main/java/org/apache/tika/metadata/XMPRights.java (1 line):
	- line 62: * TODO This is actually a language alternative property


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmItspHeader.java (1 line):
	- line 41: // TODO: refactor all unmarshals


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp3/ID3v2Frame.java (1 line):
	- line 183: // TODO Log the short read


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/msg/ExtendedMetadataExtractor.java (1 line):
	- line 314: //TODO:


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/audio/AudioParser.java (1 line):
	- line 92: // TODO: Use XMPDM.TRACKS? (see also frame rate in AudioFormat)


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/XMLErrorLogUpdater.java (1 line):
	- line 163: //TODO: log


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/renderer/pdf/pdfbox/PDFBoxRenderer.java (1 line):
	- line 165: //TODO: parameterize whether or not to un-rotate page?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/PagesContentHandler.java (1 line):
	- line 380: // TODO Can there be custom ones?


tika-parsers/tika-parsers-extended/tika-parser-scientific-module/src/main/java/org/apache/tika/parser/gdal/GDALParser.java (1 line):
	- line 224: // TODO: investigate a way to do both using ExternalParser


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/UnrarParser.java (1 line):
	- line 103: //TODO: process stdout to extract status for each file:


tika-core/src/main/java/org/apache/tika/metadata/Metadata.java (1 line):
	- line 374: //TODO: optimize this to not copy if all


tika-pipes/tika-emitters/tika-emitter-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitter.java (1 line):
	- line 181: //TODO -- add other params to the builder as needed


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/wordperfect/WP6DocumentAreaExtractor.java (1 line):
	- line 140: //TODO Are there functions containing data? Like footnotes?


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/ByteInjector.java (1 line):
	- line 45: //TODO -- don't load the full thing into memory


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/reports/Report.java (1 line):
	- line 48: final String NULL_VALUE = "";//TODO: make this configurable!!!


tika-eval/tika-eval-app/src/main/java/org/apache/tika/eval/app/FileProfiler.java (1 line):
	- line 57: //TODO: we should allow users to select digest type/encoding and file detector(s).


tika-core/src/main/java/org/apache/tika/detect/DefaultProbDetector.java (1 line):
	- line 31: * TODO Link to documentation on configuring these probabilities


tika-parsers/tika-parsers-ml/tika-age-recogniser/src/main/java/org/apache/tika/parser/recognition/AgeRecogniser.java (1 line):
	- line 81: //TODO: what do we want to check here?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/XFAExtractor.java (1 line):
	- line 79: //TODO - replace this with multivalued map? This isn't


tika-translate/src/main/java/org/apache/tika/language/translate/impl/YandexTranslator.java (1 line):
	- line 101: //TODO Add support for text over 10k characters


tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/tf/TensorflowImageRecParser.java (1 line):
	- line 157: //TODO -- what do we want to check?


tika-core/src/main/java/org/apache/tika/metadata/TikaCoreProperties.java (1 line):
	- line 412: THUMBNAIL, //TODO: set this in parsers that handle thumbnails


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/detect/gzip/GZipSpecializationDetector.java (1 line):
	- line 87: //TODO: something better than this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteTreeWalker.java (1 line):
	- line 523: //TODO -- these seem to be somewhat broken font files and other


tika-detectors/tika-detector-siegfried/src/main/java/org/apache/tika/detect/siegfried/SiegfriedDetector.java (1 line):
	- line 75: //TODO -- grab errors and warnings


tika-core/src/main/java/org/apache/tika/metadata/Photoshop.java (1 line):
	- line 41: // TODO Replace this with proper indexed choices support


tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JInceptionV3Net.java (1 line):
	- line 283: //TODO: what do we want to check here?


tika-batch/src/main/java/org/apache/tika/batch/fs/FSOutputStreamFactory.java (1 line):
	- line 73: //TODO: shouldn't need this any more in java 7, right?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java (1 line):
	- line 96: //TODO: should we do a singleton for dwfx+xps?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/RunProperties.java (1 line):
	- line 68: //TODO -- fill out rest


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/DefaultHtmlMapper.java (1 line):
	- line 112: // TODO - fill out this set. Include core, i18n, etc sets where appropriate.


tika-core/src/main/java/org/apache/tika/language/detect/LanguageDetector.java (1 line):
	- line 35: // TODO decide how deep to go into supporting extended language tags, see


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/video/FLVParser.java (1 line):
	- line 239: // TODO if there are multiple metadata values with same key (in


tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java (1 line):
	- line 93: //TODO: what do we want to check here?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/detect/ole/MiscOLEDetector.java (1 line):
	- line 39: * TODO: refactor this copy/paste from POIFSContainerDetector


tika-batch/src/main/java/org/apache/tika/batch/fs/builders/FSCrawlerBuilder.java (1 line):
	- line 75: //TODO: change to logger warn or throw RuntimeException?


tika-core/src/main/java/org/apache/tika/metadata/PagedText.java (1 line):
	- line 36: //TODO MaxPageSize, Fonts, Colorants, PlateNames


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/main/java/org/apache/tika/parser/mbox/MboxParser.java (1 line):
	- line 213: // TODO - key off content-type in headers to


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java (1 line):
	- line 89: // TODO: we should make this dynamic depending on the size of the image


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/wordperfect/WP5Charsets.java (1 line):
	- line 168: //TODO map multi-characters


tika-langdetect/tika-langdetect-tika/src/main/java/org/apache/tika/langdetect/tika/LanguageProfilerBuilder.java (1 line):
	- line 127: // TODO: Compute the initial capacity using minlen and maxlen.


tika-parsers/tika-parsers-extended/tika-parser-sqlite3-module/src/main/java/org/apache/tika/parser/sqlite3/SQLite3DBParser.java (1 line):
	- line 158: //TODO -- figure out how to get the version of sqlite3 that last modified this file and


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/OldExcelParser.java (1 line):
	- line 83: // TODO Get the version and type, to set as the Content Type


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java (1 line):
	- line 339: //TODO add metadata about iframe content?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xmp-commons/src/main/java/org/apache/tika/parser/xmp/XMPMetadataExtractor.java (1 line):
	- line 89: //TODO PDFBOX30 this segment no longer needed with 3.0


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java (1 line):
	- line 81: //TODO find what happened to SUPPORTED_TYPES


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/pst/PSTMailItemParser.java (1 line):
	- line 123: //if there's no html, back off to straight text -- TODO maybe add RTF parsing?


tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentByteStoreExtractorFactory.java (1 line):
	- line 29: * TODO: Figure out how to simplify this and allow for emitting of the source document.


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/strings/StringsParser.java (1 line):
	- line 159: // TODO Resolve it so we don't need this try/catch block


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/main/java/org/apache/tika/parser/wacz/WACZParser.java (1 line):
	- line 100: //TODO -- process pages (jsonl); process indexes?!


tika-core/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcher.java (1 line):
	- line 109: //TODO extract owner or group?


tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/TlsConfig.java (1 line):
	- line 29: //TODO make this configurable


tika-core/src/main/java/org/apache/tika/utils/CharsetUtils.java (1 line):
	- line 78: // TODO: would be nice to somehow log that we


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/detect/microsoft/POIFSContainerDetector.java (1 line):
	- line 344: //TODO -- create a mime for active x


tika-pipes/tika-pipes-iterators/tika-pipes-iterator-jdbc/src/main/java/org/apache/tika/pipes/pipesiterator/jdbc/JDBCPipesIterator.java (1 line):
	- line 282: //TODO: improve this later with special handling for numerals/dates/timestamps, etc


tika-parsers/tika-parsers-ml/tika-transcribe-aws/src/main/java/org/apache/tika/parser/transcribe/aws/AmazonTranscribe.java (1 line):
	- line 395: //TODO alert user if they've gotten 1 or 2 out of three?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java (1 line):
	- line 657: * TODO When POI 3.18 is out, replace this with PictureRunMapper,


tika-pipes/tika-httpclient-commons/src/main/java/org/apache/tika/client/HttpClientFactory.java (1 line):
	- line 438: //TODO: sha-256?


tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java (1 line):
	- line 76: // TODO: Add all supported video types


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/Truncator.java (1 line):
	- line 43: //TODO -- redo streaming


tika-core/src/main/java/org/apache/tika/fork/ForkParser.java (1 line):
	- line 326: //TODO: make this more useful


tika-parsers/tika-parsers-ml/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/sentiment/SentimentAnalysisParser.java (1 line):
	- line 114: //TODO -- what do we want to check?


tika-pipes/tika-pipes-reporters/tika-pipes-reporter-opensearch/src/main/java/org/apache/tika/pipes/reporters/opensearch/OpenSearchPipesReporter.java (1 line):
	- line 89: //TODO -- we're not currently doing anything with the message


tika-pipes/tika-pipes-iterators/tika-pipes-iterator-s3/src/main/java/org/apache/tika/pipes/pipesiterator/s3/S3PipesIterator.java (1 line):
	- line 200: //TODO -- allow user specified metadata as the "id"?


tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/HTMLHelper.java (1 line):
	- line 30: * TODO Decide if this would be better done as a MessageBodyWriter


tika-parsers/tika-parsers-ml/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/ner/NamedEntityParser.java (1 line):
	- line 82: //TODO: read class name from context or config


tika-translate/src/main/java/org/apache/tika/language/translate/impl/CachedTranslator.java (1 line):
	- line 161: // TODO what to do if we get an error?


tika-batch/src/main/java/org/apache/tika/batch/fs/builders/BasicTikaFSConsumersBuilder.java (1 line):
	- line 242: //TODO: possibly open up the different handle-existings in the future


tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java (1 line):
	- line 117: //TODO: figure out if the rw lock is any better than a simple lock


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/fsshttpb/MSOneStorePackage.java (1 line):
	- line 248: //TODO -- these seem to be somewhat broken font files and other


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dbf/DBFParser.java (1 line):
	- line 123: //TODO: potentially use codepage info in the header


tika-xmp/src/main/java/org/apache/tika/xmp/convert/GenericConverter.java (1 line):
	- line 86: // TODO Add support for structs and lang-alts, but those types are


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/JackcessParser.java (1 line):
	- line 63: //TODO: figure out how to get this info


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java (1 line):
	- line 315: //TODO: find an example where basic.getThumbNail is not null


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/iwork/iwana/IWork13PackageParser.java (1 line):
	- line 323: // TODO Decode the snappy stream, and check for the Message Type


tika-core/src/main/java/org/apache/tika/pipes/emitter/Emitter.java (1 line):
	- line 32: //TODO -- add this later for xhtml?


tika-xmp/src/main/java/org/apache/tika/xmp/XMPMetadata.java (1 line):
	- line 320: // TODO Timezone is currently lost


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/GeneralTransformer.java (1 line):
	- line 81: //TODO -- make this actually streaming


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java (1 line):
	- line 566: //TODO: consider allowing multiple text pieces


tika-serialization/src/main/java/org/apache/tika/serialization/TikaJsonSerializer.java (1 line):
	- line 160: //Also, TODO -- this should favor getters and setters with Strings over those


tika-core/src/main/java/org/apache/tika/metadata/writefilter/StandardWriteFilter.java (1 line):
	- line 224: //TODO: should we limit the number of field values?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/Icu4jEncodingDetector.java (1 line):
	- line 66: // TODO: log a warning?


tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java (1 line):
	- line 112: //TODO: consider adding others...


tika-core/src/main/java/org/apache/tika/detect/TrainedModelDetector.java (1 line):
	- line 91: // TODO: any reason to avoid closing of input & inputChannel?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java (1 line):
	- line 100: // TODO: we should probably add a readlimiting wrapper around this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmExtractor.java (1 line):
	- line 279: // TODO: Improve the caching


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java (1 line):
	- line 268: //SEE TIKA-2703 TODO: add unit test


tika-core/src/main/java/org/apache/tika/config/ConfigBase.java (1 line):
	- line 301: //TODO -- we could do more with info from the node -- is it complex, does it have


tika-core/src/main/java/org/apache/tika/detect/FileCommandDetector.java (1 line):
	- line 59: //TODO: file has some diff mimes names for some very common mimes


tika-core/src/main/java/org/apache/tika/pipes/pipesiterator/PipesIterator.java (1 line):
	- line 176: //TODO: make throwOnWriteLimitReached configurable


tika-server/tika-server-core/src/main/resources/tikaserver-template.html (1 line):
	- line 24: <!-- TODO Some nice CSS -->


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/DataURISchemeUtil.java (1 line):
	- line 65: //TODO: handle encodings


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/main/java/org/apache/tika/detect/apple/BPListDetector.java (1 line):
	- line 121: //TODO: extract the version with the next two bytes if they were read


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/dbf/DBFFileHeader.java (1 line):
	- line 71: IOUtils.skipFully(is, 20);//TODO: can get useful info out of here


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/chm/ChmLzxState.java (1 line):
	- line 68: //TODO: position_slots is not used ?


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/epub/EpubContentParser.java (1 line):
	- line 38: * For the time being, assume XHTML (TODO: DTBook)


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/parser/pkg/PackageParser.java (1 line):
	- line 277: //TODO -- we've probably already detected the stream by here. We should


tika-core/src/main/java/org/apache/tika/detect/NNTrainedModel.java (1 line):
	- line 62: // TODO Auto-generated method stub


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/OneNoteParser.java (1 line):
	- line 68: // TODO - add onetoc and other onenote mime types


tika-batch/src/main/java/org/apache/tika/batch/builders/DefaultContentHandlerFactoryBuilder.java (1 line):
	- line 50: //TODO: should we throw a RuntimeException?


tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java (1 line):
	- line 95: //TODO -- what do we want to check?


tika-core/src/main/java/org/apache/tika/metadata/XMPMM.java (1 line):
	- line 35: * TODO This property is of type RessourceRef which is a struct


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLTikaBodyPartHandler.java (1 line):
	- line 55: //TODO: fix this


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetRecog_UTF8.java (1 line):
	- line 88: // TODO: add plain ASCII as an explicitly detected type.


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/main/java/org/apache/tika/detect/zip/OpenDocumentDetector.java (1 line):
	- line 65: //odt -- TODO -- check that the results are valid


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/txt/CharsetDetector.java (1 line):
	- line 275: //   TODO:  A better implementation would be to copy the detect loop from


tika-core/src/main/java/org/apache/tika/metadata/WARC.java (1 line):
	- line 30: //TODO: lots


tika-fuzzing/src/main/java/org/apache/tika/fuzzing/cli/FuzzingCLI.java (1 line):
	- line 136: //TODO - parameterize this


tika-core/src/main/java/org/apache/tika/renderer/RenderResult.java (1 line):
	- line 41: //TODO: we're relying on metadata to bring in a bunch of info.


tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/wordperfect/QPWTextExtractor.java (1 line):
	- line 99: //TODO shall we validate and throw warning/error if the file does not