#!/usr/bin/env python3
#
# (c) 2017 Fetal-Neonatal Neuroimaging & Developmental Science Center
#                   Boston Children's Hospital
#
#              http://childrenshospital.org/FNNDSC/
#                        dev@babyMRI.org
#

import sys, os
sys.path.insert(1, os.path.join(os.path.dirname(__file__), '../pfdicom_tagExtract'))

import  pfdicom_tagExtract
from    argparse            import RawTextHelpFormatter
from    argparse            import ArgumentParser
import  pudb

import  pfmisc
from    pfmisc._colors      import Colors
from    pfmisc              import other

str_version = "2.2.24"
str_desc = Colors.CYAN + """


        __    _ _                      _              _____     _                  _
       / _|  | (_)                    | |            |  ___|   | |                | |
 _ __ | |_ __| |_  ___ ___  _ __ ___  | |_ __ _  __ _| |____  _| |_ _ __ __ _  ___| |_
| '_ \|  _/ _` | |/ __/ _ \| '_ ` _ \ | __/ _` |/ _` |  __\ \/ / __| '__/ _` |/ __| __|
| |_) | || (_| | | (_| (_) | | | | | || || (_| | (_| | |___>  <| |_| | | (_| | (__| |_
| .__/|_| \__,_|_|\___\___/|_| |_| |_| \__\__,_|\__, \____/_/\_\\__|_|  \__,_|\___|\__|
| |                                ______        __/ |
|_|                               |______|      |___/


                        Path-File DICOM tag extactor

        Recursively walk down a directory tree and extract DICOM tags,
        writing report files preserving directory structure in output tree.

                             -- version """ + \
             Colors.YELLOW + str_version + Colors.CYAN + """ --

        'pfdicom_tagExtract' is a customizable and friendly DICOM tag extractor.
        As part of the "pf*" suite of applications, it is geared to IO as
        directories. Input DICOM trees are reconstructed in an output
        directory, preserving directory structure. Each node tree contains
        report files on the corresponding input location's DICOM files.


""" + Colors.NO_COLOUR

def synopsis(ab_shortOnly = False):
    scriptName = os.path.basename(sys.argv[0])
    shortSynopsis =  '''
    NAME

	    pfdicom_tagExtract
        - process DICOM file header information down a file system tree.

    SYNOPSIS

            pfdicom_tagExtract                                      \\
                     -I|--inputDir <inputDir>                       \\
                    [-i|--inputFile <inputFile>]                    \\
                    [-e|--extension <DICOMextension>]               \\
                    [-F|--tagFile <tagFile>] |                      \\
                    [-T|--tagList <tagList>] |                      \\
                    [-m|--image <imageFile>]                        \\
                     -O|--outputDir <outputDir>                     \\
                     -o|--output <outputFileStem>                   \\
                    [-s|--imageScale <factor>[:<interpolation>]]    \\
                    [-t|--outputFileType <outputFileType>           \\
                    [--threads <numThreads>]                        \\
                    [-p|--printToScreen]                            \\
                    [--json]                                        \\
                    [--useIndexhtml]                                \\
                    [-v <verbosity>]                                \\
                    [--followLinks]                                 \\
                    [--version]                                     \\
                    [-x|--man]                                      \\
                    [-y|--synopsis]

    BRIEF EXAMPLE

        pfdicom_tagExtract                                          \\
                    -I /var/www/html/normsmall -e dcm               \\
                    -O /var/www/html/tag                            \\
                    -o '%_md5|6_PatientID-%PatientAge'              \\
                    -m 'm:%_md5|6_PatientID-%PatientAge.jpg'        \\
                    -t raw,json,html,dict,col,csv                   \\
                    --threads 0 -v 1

    '''

    description =  '''
    DESCRIPTION

        `pfdicom_tagExtract` extracts the header information of DICOM files
        and echoes to stdout as well as to an output report-type file -- this
        can be a raw output, a json-type output, or html-type output.

        The script accepts an <inputDir>, and then from this point an os.walk
        is performed to extract all the subdirs. Each subdir is examined for
        DICOM files (in the simplest sense by a file extension mapping) and
        either the head, tail, middle (or other indexed) file is examined for
        its tag information.

        Optionally, the tag list can be constrained either by passing a
        <tagFile> containing a line-by-line list of tags to query, or
        by passing a comma separated list of tags directly.

        Finally, an image conversion can also be performed (and embedded
        within the output html file, if an html conversion is specified).

    ARGS

        -I|--inputDir <inputDir>
        Input DICOM directory to examine. By default, the first file in this
        directory is examined for its tag information. There is an implicit
        assumption that each <inputDir> contains a single DICOM series.

        [-i|--inputFile <inputFile>]
        An optional <inputFile> specified relative to the <inputDir>. If
        specified, then do not perform a directory walk, but convert only
        this file.

        [-e|--extension <DICOMextension>]
        An optional extension to filter the DICOM files of interest from the
        <inputDir>.

        -O|--outputDir <outputDir>
        The output root directory that will contain a tree structure identical
        to the input directory, and each "leaf" node will contain the analysis
        results.

        [--outputLeafDir <outputLeafDirFormat>]
        If specified, will apply the <outputLeafDirFormat> to the output
        directories containing data. This is useful to blanket describe
        final output directories with some descriptive text, such as
        'anon' or 'preview'.

        This is a formatting spec, so

            --outputLeafDir 'preview-%%s'

        where %%s is the original leaf directory node, will prefix each
        final directory containing output with the text 'preview-' which
        can be useful in describing some features of the output set.

        [-F|--tagFile <tagFile>]
        Read the tags, one-per-line in <tagFile>, and print the
        corresponding tag information in the DICOM <inputFile>.

        [-T|--tagList <tagList>]
        Read the list of comma-separated tags in <tagList>, and print the
        corresponding tag information parsed from the DICOM <inputFile>.

        [-m|--image <[<index>:]imageFile>]
        If specified, also convert the <inputFile> to <imageFile>. If the
        name is preceded by an index and colon, then convert this indexed
        file in the particular <inputDir>.

        [-s|--imageScale <factor>[:<interpolation>]]
        If an image conversion is specified, this flag will scale the image
        by <factor> and use an interpolation <order>. This is useful in
        increasing the size of images for the html output.

        Note that certain interpolation choices can result in a significant
        slowdown!

            interpolation order:

            'none', 'nearest', 'bilinear', 'bicubic', 'spline16',
            'spline36', 'hanning', 'hamming', 'hermite', 'kaiser', 'quadric',
            'catrom', 'gaussian', 'bessel', 'mitchell', 'sinc', 'lanczos'

        -o|--outputFileStem <outputFileStem>
        The output file stem to store data. This should *not* have a file
        extension, or rather, any "." in the name are considered part of
        the stem and are *not* considered extensions.

        [-t|--outputFileType <outputFileType>]
        A comma specified list of output types. These can be:

            o <type>    <ext>       <desc>
            o raw       -raw.txt    the raw internal dcm structure to string
            o json      .json       a json representation
            o html      .html       an html representation with optional image
            o dict      -dict.txt   a python dictionary
            o col       -col.txt    a two-column text representation (tab sep)
            o csv       .csv        a csv representation

        Note that if not specified, a default type of 'raw' is assigned.

        [-p|--printToScreen]
        If specified, will print tags to screen.

        [--threads <numThreads>]
        If specified, break the innermost analysis loop into <numThreads>
        threads.

        [--useIndexhtml]
        If specified, force the name of any output html reports to be
        'index.html'.

        [-x|--man]
        Show full help.

        [-y|--synopsis]
        Show brief help.

        [--version]
        If specified, print the version number and exit.

        [--json]
        If specified, output a JSON dump of final return.

        [--followLinks]
        If specified, follow symbolic links.

        [-v|--verbosity <level>]
        Set the app verbosity level.

            0: No internal output;
            1: Run start / stop output notification;
            2: As with level '1' but with simpleProgress bar in 'pftree';
            3: As with level '2' but with list of input dirs/files in 'pftree';
            5: As with level '3' but with explicit file logging for
                    - read
                    - analyze
                    - write

    EXAMPLES

    Extract DICOM header info down an input tree and save reports
    to output tree:

        pfdicom_tagExtract                                      \\
                    -I /var/www/html/normsmall -e dcm           \\
                    -O /var/www/html/tag                        \\
                    -o '%_md5|6_PatientID-%PatientAge'          \\
                    -m 'm:%_nospc|-_ProtocolName.jpg'           \\
                    -s 3:none                                   \\
                    --useIndexhtml                              \\
                    -t raw,json,html,dict,col,csv               \\
                    --threads 0 -v 0 --json

        which will output only at script conclusion and will log a JSON
        formatted string.

    '''
    if ab_shortOnly:
        return shortSynopsis
    else:
        return shortSynopsis + description



parser  = ArgumentParser(description = str_desc, formatter_class = RawTextHelpFormatter)

parser.add_argument("-I", "--inputDir",
                    help    = "input dir",
                    dest    = 'inputDir')
parser.add_argument("-i", "--inputFile",
                    help    = "input file",
                    dest    = 'inputFile',
                    default = '')
parser.add_argument("-e", "--extension",
                    help    = "DICOM file extension",
                    dest    = 'extension',
                    default = '')
parser.add_argument("-F", "--tagFile",
                    help    = "file containing tags to parse",
                    dest    = 'tagFile',
                    default = '')
parser.add_argument("-T", "--tagList",
                    help    = "comma-separated tag list",
                    dest    = 'tagList',
                    default = '')
parser.add_argument("-r",
                    help    = "display raw tags",
                    dest    = 'rawType',
                    default = 'raw')
parser.add_argument("-m", "--imageFile",
                    help    = "image file to convert DICOM input",
                    dest    = 'imageFile',
                    default = '')
parser.add_argument("-s", "--imageScale",
                    help    = "scale images with factor and optional :interpolation",
                    dest    = 'imageScale',
                    default = '')
parser.add_argument("-o", "--outputFileStem",
                    help    = "output file stem",
                    default = "",
                    dest    = 'outputFileStem')
parser.add_argument("-O", "--outputDir",
                    help    = "output image directory",
                    dest    = 'outputDir',
                    default = '')
parser.add_argument("-t", "--outputFileType",
                    help    = "list of output report types",
                    dest    = 'outputFileType',
                    default = 'raw')
parser.add_argument("--printElapsedTime",
                    help    = "print program run time",
                    dest    = 'printElapsedTime',
                    action  = 'store_true',
                    default = False)
parser.add_argument("--useIndexhtml",
                    help    = "force html file to be called 'index.html'",
                    dest    = 'useIndexhtml',
                    action  = 'store_true',
                    default = False)
parser.add_argument("-p", "--printToScreen",
                    help    = "print output to screen",
                    dest    = 'printToScreen',
                    action  = 'store_true',
                    default = False)
parser.add_argument("-x", "--man",
                    help    = "man",
                    dest    = 'man',
                    action  = 'store_true',
                    default = False)
parser.add_argument("-y", "--synopsis",
                    help    = "short synopsis",
                    dest    = 'synopsis',
                    action  = 'store_true',
                    default = False)
parser.add_argument("--threads",
                    help    = "number of threads for innermost loop processing",
                    dest    = 'threads',
                    default = "0")
parser.add_argument("--outputLeafDir",
                    help    = "formatting spec for output leaf directory",
                    dest    = 'outputLeafDir',
                    default = "")
parser.add_argument("-v", "--verbosity",
                    help    = "verbosity level for app",
                    dest    = 'verbosity',
                    default = "0")
parser.add_argument('--version',
                    help    = 'if specified, print version number',
                    dest    = 'b_version',
                    action  = 'store_true',
                    default = False)
parser.add_argument("--followLinks",
                    help    = "follow symbolic links",
                    dest    = 'followLinks',
                    action  = 'store_true',
                    default = False)
parser.add_argument("--json",
                    help    = "output final return in json",
                    dest    = 'json',
                    action  = 'store_true',
                    default = False)
args = parser.parse_args()

if args.man or args.synopsis:
    print(str_desc)
    if args.man:
        str_help     = synopsis(False)
    else:
        str_help     = synopsis(True)
    print(str_help)
    sys.exit(1)

if args.b_version:
    print("Version: %s" % str_version)
    sys.exit(1)

# pudb.set_trace()

pf_dicom_tagExtract = pfdicom_tagExtract.pfdicom_tagExtract(
                        inputDir            = args.inputDir,
                        inputFile           = args.inputFile,
                        extension           = args.extension,
                        outputDir           = args.outputDir,
                        outputFileStem      = args.outputFileStem,
                        outputLeafDir       = args.outputLeafDir,
                        useIndexhtml        = args.useIndexhtml,
                        outputFileType      = args.outputFileType,
                        tagFile             = args.tagFile,
                        tagList             = args.tagList,
                        printToScreen       = args.printToScreen,
                        threads             = args.threads,
                        imageFile           = args.imageFile,
                        imageScale          = args.imageScale,
                        verbosity           = args.verbosity,
                        followLinks         = args.followLinks,
                        json                = args.json,
                        version             = str_version
                    )

# And now run it!
d_pfdicom_tagExtract = pf_dicom_tagExtract.run(timerStart = True)

if args.printElapsedTime:
    pf_dicom_tagExtract.dp.qprint(
                                "Elapsed time = %f seconds" %
                                d_pfdicom_tagExtract['runTime']
                            )

sys.exit(0)
