--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/config.yml	Fri Mar 03 14:10:24 2023 +0000
@@ -0,0 +1,250 @@
+##
+## when you see {{ something }} in a string, this means the string is
+## a template, and the "{{ something }}" will be replaced by its value
+## at runtime.
+## This is usefull to build strings from other strings.
+## to reference an item in a tree, you can use dots as branches:
+##  {{ parameters.flags.help }}
+## will be extrapolated to "Show this help"
+## 
+## But beware:
+##  {{ parameters.mandatory }}
+## will be extrapolated to
+##  "{'input': 'input file path'}"
+##
+
+## this config is used for debug.
+## it allows to define debug options before everything else is parsed
+__meta_config__:
+  __debug__: False
+  __debug_stream__: stderr
+  __only_root_debug__: False
+
+
+## the cli parameters
+parameters:
+  mandatory:
+    ## input is mandatory
+    input: input file path
+  flags:
+    ## help, verbose and version can be provided with no parameter.
+    help: Show this help
+    verbose: More verbose outputs
+    version: Show this tool's version
+    debug: show debug outputs
+    do_run_dry: Runs the whole process, without the server. Usefull for tests.
+    embed_js: Embed js in html file instead of using a separated js file.
+    firefox: Open firefox on the web page.
+    chromium: Open chromium or chrome on the web page.
+  optional:
+    ## these optional parameters need a value "--opt value --opt2 value2"
+    method: "default is {{ defaults.method }}"
+    spectrum_type: "default is {{ defaults.spectrum_type }}"
+    sample_type: "default is {{ defaults.sample_type }}"
+    resolution: "default is {{ defaults.resolution }}"
+    resolution: "default is {{ defaults.resolution }}"
+    name: The precursor name
+    peakforest.url: "default={{ defaults.peakforest.url }}"
+    peakforest.token: The token to comunicate with peakforest api
+    polarity: positive|negative
+    raw_metadata: example - 1-1__INCHIKEY__=QNAYBMKLOCPYGJ-REOHCLBHSA-N_L-Alanine_MS_POS_plasma_RT__=0.84_filtree.csv
+    scan_type: ms|msms|rmn
+    run_dry_html: when "--run-dry", provides the output directory for {{ generated.html }}
+    run_dry_js: when "--run-dry", provides the output directory for {{ generated.js }}
+    raw_metadata_sep: "raw metadata separator"
+    logging.std: "Either out, err, or anything else to not output"
+    logging.file.path: "The file path to output logs to"
+    validation: "Set the default validation to the provided value, TRUE or FALSE."
+    output_json: "Provide a path to output a JSON file."
+  meta:
+    ## meta info about the tool itself
+    author: Lain Pavot
+    version: 1.1.0
+  shortcuts:
+    ## to define things like: "we can use -p instead of --polarity"
+    peakforest.token: t
+    polarity: p
+    help: h
+    version: v
+    verbose: V
+    debug: d
+    logging.std: l
+
+## some default parameters
+## logging defines two elements: std and file.
+## std should be either empty, err or out.
+## it tells where to outputs logs:
+##   - nowhere (empty value)
+##   - in sterr (err)
+##   - in stdout (out)
+## and file. Id a path is provided, add outputs to this file.
+## if append is true, outputs are appended to the file.
+## otherwise, the file is emptied each time the app runs.
+defaults:
+  peakforest:
+    url: https://nightly.peakforest.org
+    token: ''
+  spectrum_type: LC_MSMS
+  method: cf_pfem_urine_method1_qtof-msms
+    # api-msms-fia__idf-cea
+    # cf_pfem_plasma_method1_qtof-msms
+    # cf_pfem_urine_method1_qtof-msms
+    # lc-msms__test
+  scan_type: ms2
+  resolution: high
+  sample_type: compound-ref
+  # sample_type: compound-mix
+  polarity: positive
+  raw_metadata: ''
+  name: ''
+  run_dry_html:
+  run_dry_js:
+  raw_metadata_sep: ','
+  validation: "TRUE"
+  verbose: false
+  debug: true
+  logging: 
+    std: out ## out || err
+    file: 
+      path:
+      append: False
+  output_json: ''
+
+## token related info
+token:
+  ## do you use a file to store your token?
+  use_file: false
+  ## if so, what path the file is located at?
+  file_path: .token
+  ## if not, you can provide you token here
+  value:
+
+network:
+  ip: 0.0.0.0
+  port: 8000
+
+workdir:
+  ## create a tmp directory
+  create_tmp: true
+  ## works in the created tmp directory, or if not created, in /tmp
+  work_in_tmp: true
+  ## generate outputs in the created tmp directory, or if not created, in /tmp
+  generate_in_tmp: true
+
+## the templates paths
+templates:
+  ## meta is what wrapps the whole page.
+  main: meta.html
+  main_mix: meta-compound-mix.html
+  main_ref: meta-compound-ref.html
+  ## form is one instance of a pf form
+  # form: form.html
+  # form: compound-ref.html
+  form: form.html
+  form_mix: compound-mix.html
+  form_ref: compound-ref.html
+  ## one item of the tab list
+  tab_list: tab_list.html
+  ## the js for one form
+  js: add-one-spectrum-index.js
+  ## placeholders for the html templates.
+  ## this will not change the placeholders syntax for this file.
+  placeholders:
+    start: "{{ "
+    stop: " }}"
+
+generated:
+  ## what filename to give to the whole html file
+  html: pf.html
+  ## what filename to give to js files
+  js: add-one-spectrum-{{ index }}.js
+
+regex:
+  values:
+    ## reuse these smol regex in bigger regex!
+    spectrum_type: "NMR|LC_MS|LC_MSMS|MRM(_\\d+)?"
+    matrix: "[Uu]rine|[Pp]lasma|[Pp]las"
+    mode: "POS|NEG"
+    energy: "\\d+ev"
+    pool: "[Pp]ool\\d+"
+    rt: "\\d+\\.\\d+"
+    runs: "\\d+-\\d+"
+    inchikey: "[A-Z]{14}-[A-Z]{10}-[A-Z]"
+
+  ## the "INCHIKEY" word
+  ## one or more underscores
+  ## may be followed by a equal sign
+  ## captures in the "inchikey" variable:
+  ##    14, 10 and 1 letters
+  ##    in caps
+  ##    separated by a hyphen
+  inchikey: "INCHIKEY_+=?(?P<inchikey>{{ regex.values.inchikey }})"
+
+  ## method is one of values defined bellow, between underscores
+  spectrum_type: "_(?P<method>{{ regex.values.method }})_"
+
+  ## matrix is one of values defined bellow, between underscores
+  matrix: "_(?P<matrix>{{ regex.values.matrix }})_"
+
+  ## pool is one of values defined bellow, between underscores
+  pool: "_(?P<pool>{{ regex.values.pool }})_"
+
+  ## molecule everything between inchikey and method.
+  molecule: "{{ regex.inchikey }}_(?P<molecule>.*?){{ regex.method }}"
+
+  ## mode is one of values defined bellow, between underscores
+  mode: "_(?P<mode>{{ regex.values.mode }})_"
+
+  ## energy is one of values defined bellow, between underscores
+  energy: "_(?P<energy>{{ regex.values.energy }})_"
+
+  ##  - A underscore,
+  ##  - the "RT" word,
+  ##  - some underscore(s),
+  ##  - an optional interrogation mark,
+  ##  - the actual RT value is captured here,
+  ##  - there is a underscore at the end
+  rt: "_RT_+=?(?P<rt>{{ regex.values.rt }})_"
+
+  ## "runs" is at the beginning, and ends with an underscore.
+  runs: "^(?P<runs>{{ regex.values.runs }})_"
+
+
+  ## BEGIN
+  ## anything
+  ## the inchikey
+  ## anything else can follow
+  ## END
+  # fragnot: ^.*{{ regex.inchikey }}.*$
+
+
+  ## This is the most exhaustive regex I came with to extract info from
+  ## fragnot files name.
+  # fragnot:
+  #   ^
+  #   .*                                (?# there may be anything at the begining)
+  #   (?P<runs>\d+-\d+)                 (?# the run numbers)
+  #   _+                                (?# followed by anything - underscores usualy)
+  #   INCHIKEY_+=?(?P<inchikey>{{ regex.inchikey }})              (?# we insert inchikey regex here - see above)
+  #   _+                                (?# there is one or more underscores)
+  #   (?P<molecule>.*?)                 (?# the molecule name follows the inchikey)
+  #   _+                                (?# there is one or more underscores)
+  #   (?P<method>{{ regex.method }})    (?# then, there is the method - nmr, ms or mrm???)
+  #   _+                                (?# there may be some underscores to separate)
+  #   (?P<matrix>{{ regex.matrix }})?   (?# the matrix - urine or plasma)
+  #   _*                                (?# there may be some underscores to separate)
+  #   (?P<mode>POS|NEG)                 (?# the acq mode - pos or neg)
+  #   _+                                (?# there may be some underscores to separate)
+  #   (?P<pool>{{ regex.pool }})?       (?# the pool - "Pool"+numbers, optional)
+  #   _*                                (?# there may be some underscores to separate)
+  #   (?P<energy>\d+ev)?                (?# the energy - only for nmr, so it's optional)
+  #   _*                                (?# there may be some underscores to separate)
+  #   (?P<pool2>{{ regex.pool }})?      (?# the pool - sometimes the pool if *after* the energy...)
+  #   _*                                (?# there may be some underscores to separate)
+  #   (?P<matrix2>{{ regex.matrix }})?  (?# the matrix is here, sometimes)
+  #   _*                                (?# there may be anything here)
+  #   RT_+=?(?P<rt>\d+\.\d+)            (?# the retension time is a decimal number)
+  #   _*                                (?# there may be anything at the end)
+  #   (?P<filtered>[fF]iltree)?         (?# sometimes, "Filtree" appears, lets capture it)
+  #   \.[ct]sv                          (?# the extension)
+  #   $
\ No newline at end of file