summary refs log tree commit diff stats
path: root/lib/pure/uri.nim
blob: abb1a462d8567353a6ddffe42bb742281f4a21ad (plain) (blame)
1
2
3pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
# goofbot

A hackish IRC bot in golang
ef='#n182'>182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444
#
#
#            Nim's Runtime Library
#        (c) Copyright 2015 Dominik Picheta
#
#    See the file "copying.txt", included in this
#    distribution, for details about the copyright.
#

## This module implements URI parsing as specified by RFC 3986.

import strutils, parseutils
type
  Url* = distinct string

  Uri* = object
    scheme*, username*, password*: string
    hostname*, port*, path*, query*, anchor*: string
    opaque*: bool

{.deprecated: [TUrl: Url, TUri: Uri].}

{.push warning[deprecated]: off.}
proc `$`*(url: Url): string {.deprecated.} =
  ## **Deprecated since 0.9.6**: Use ``Uri`` instead.
  return string(url)

proc `/`*(a, b: Url): Url {.deprecated.} =
  ## Joins two URLs together, separating them with / if needed.
  ##
  ## **Deprecated since 0.9.6**: Use ``Uri`` instead.
  var urlS = $a
  var bS = $b
  if urlS == "": return b
  if urlS[urlS.len-1] != '/':
    urlS.add('/')
  if bS[0] == '/':
    urlS.add(bS.substr(1))
  else:
    urlS.add(bs)
  result = Url(urlS)

proc add*(url: var Url, a: Url) {.deprecated.} =
  ## Appends url to url.
  ##
  ## **Deprecated since 0.9.6**: Use ``Uri`` instead.
  url = url / a
{.pop.}

proc parseAuthority(authority: string, result: var Uri) =
  var i = 0
  var inPort = false
  while true:
    case authority[i]
    of '@':
      swap result.password, result.port
      result.port.setLen(0)
      swap result.username, result.hostname
      result.hostname.setLen(0)
      inPort = false
    of ':':
      inPort = true
    of '\0': break
    else:
      if inPort:
        result.port.add(authority[i])
      else:
        result.hostname.add(authority[i])
    i.inc

proc parsePath(uri: string, i: var int, result: var Uri) =

  i.inc parseUntil(uri, result.path, {'?', '#'}, i)

  # The 'mailto' scheme's PATH actually contains the hostname/username
  if result.scheme.toLower == "mailto":
    parseAuthority(result.path, result)
    result.path.setLen(0)

  if uri[i] == '?':
    i.inc # Skip '?'
    i.inc parseUntil(uri, result.query, {'#'}, i)

  if uri[i] == '#':
    i.inc # Skip '#'
    i.inc parseUntil(uri, result.anchor, {}, i)

proc initUri*(): Uri =
  ## Initializes a URI.
  result = Uri(scheme: "", username: "", password: "", hostname: "", port: "",
                path: "", query: "", anchor: "")

proc resetUri(uri: var Uri) =
  for f in uri.fields:
    when f is string:
      f.setLen(0)
    else:
      f = false

proc parseUri*(uri: string, result: var Uri) =
  ## Parses a URI. The `result` variable will be cleared before.
  resetUri(result)

  var i = 0

  # Check if this is a reference URI (relative URI)
  let doubleSlash = uri.len > 1 and uri[1] == '/'
  if uri[i] == '/':
    # Make sure ``uri`` doesn't begin with '//'.
    if not doubleSlash:
      parsePath(uri, i, result)
      return

  # Scheme
  i.inc parseWhile(uri, result.scheme, Letters + Digits + {'+', '-', '.'}, i)
  if uri[i] != ':' and not doubleSlash:
    # Assume this is a reference URI (relative URI)
    i = 0
    result.scheme.setLen(0)
    parsePath(uri, i, result)
    return
  if not doubleSlash:
    i.inc # Skip ':'

  # Authority
  if uri[i] == '/' and uri[i+1] == '/':
    i.inc(2) # Skip //
    var authority = ""
    i.inc parseUntil(uri, authority, {'/', '?', '#'}, i)
    if authority == "":
      raise newException(ValueError, "Expected authority got nothing.")
    parseAuthority(authority, result)
  else:
    result.opaque = true

  # Path
  parsePath(uri, i, result)

proc parseUri*(uri: string): Uri =
  ## Parses a URI and returns it.
  result = initUri()
  parseUri(uri, result)

proc removeDotSegments(path: string): string =
  if path.len == 0: return ""
  var collection: seq[string] = @[]
  let endsWithSlash = path[path.len-1] == '/'
  var i = 0
  var currentSegment = ""
  while true:
    case path[i]
    of '/':
      collection.add(currentSegment)
      currentSegment = ""
    of '.':
      if path[i+1] == '.' and path[i+2] == '/':
        if collection.len > 0:
          discard collection.pop()
          i.inc 3
          continue
      elif path[i+1] == '/':
        i.inc 2
        continue
      currentSegment.add path[i]
    of '\0':
      if currentSegment != "":
        collection.add currentSegment
      break
    else:
      currentSegment.add path[i]
    i.inc

  result = collection.join("/")
  if endsWithSlash: result.add '/'

proc merge(base, reference: Uri): string =
  # http://tools.ietf.org/html/rfc3986#section-5.2.3
  if base.hostname != "" and base.path == "":
    '/' & reference.path
  else:
    let lastSegment = rfind(base.path, "/")
    if lastSegment == -1:
      reference.path
    else:
      base.path[0 .. lastSegment] & reference.path

proc combine*(base: Uri, reference: Uri): Uri =
  ## Combines a base URI with a reference URI.
  ##
  ## This uses the algorithm specified in
  ## `section 5.2.2 of RFC 3986 <http://tools.ietf.org/html/rfc3986#section-5.2.2>`_.
  ##
  ## This means that the slashes inside the base URI's path as well as reference
  ## URI's path affect the resulting URI.
  ##
  ## For building URIs you may wish to use \`/\` instead.
  ##
  ## Examples:
  ##
  ## .. code-block::
  ##   let foo = combine(parseUri("http://example.com/foo/bar"), parseUri("/baz"))
  ##   assert foo.path == "/baz"
  ##
  ##   let bar = combine(parseUri("http://example.com/foo/bar"), parseUri("baz"))
  ##   assert bar.path == "/foo/baz"
  ##
  ##   let bar = combine(parseUri("http://example.com/foo/bar/"), parseUri("baz"))
  ##   assert bar.path == "/foo/bar/baz"

  template setAuthority(dest, src: expr): stmt =
    dest.hostname = src.hostname
    dest.username = src.username
    dest.port = src.port
    dest.password = src.password

  result = initUri()
  if reference.scheme != base.scheme and reference.scheme != "":
    result = reference
    result.path = removeDotSegments(result.path)
  else:
    if reference.hostname != "":
      setAuthority(result, reference)
      result.path = removeDotSegments(reference.path)
      result.query = reference.query
    else:
      if reference.path == "":
        result.path = base.path
        if reference.query != "":
          result.query = reference.query
        else:
          result.query = base.query
      else:
        if reference.path.startsWith("/"):
          result.path = removeDotSegments(reference.path)
        else:
          result.path = removeDotSegments(merge(base, reference))
        result.query = reference.query
      setAuthority(result, base)
    result.scheme = base.scheme
  result.anchor = reference.anchor

proc combine*(uris: varargs[Uri]): Uri =
  ## Combines multiple URIs together.
  result = uris[0]
  for i in 1 .. <uris.len:
    result = combine(result, uris[i])

proc `/`*(x: Uri, path: string): Uri =
  ## Concatenates the path specified to the specified URI's path.
  ##
  ## Contrary to the ``combine`` procedure you do not have to worry about
  ## the slashes at the beginning and end of the path and URI's path
  ## respectively.
  ##
  ## Examples:
  ##
  ## .. code-block::
  ##   let foo = parseUri("http://example.com/foo/bar") / parseUri("/baz")
  ##   assert foo.path == "/foo/bar/baz"
  ##
  ##   let bar = parseUri("http://example.com/foo/bar") / parseUri("baz")
  ##   assert bar.path == "/foo/bar/baz"
  ##
  ##   let bar = parseUri("http://example.com/foo/bar/") / parseUri("baz")
  ##   assert bar.path == "/foo/bar/baz"
  result = x
  if result.path[result.path.len-1] == '/':
    if path[0] == '/':
      result.path.add(path[1 .. path.len-1])
    else:
      result.path.add(path)
  else:
    if path[0] != '/':
      result.path.add '/'
    result.path.add(path)

proc `$`*(u: Uri): string =
  ## Returns the string representation of the specified URI object.
  result = ""
  if u.scheme.len > 0:
    result.add(u.scheme)
    if u.opaque:
      result.add(":")
    else:
      result.add("://")
  if u.username.len > 0:
    result.add(u.username)
    if u.password.len > 0:
      result.add(":")
      result.add(u.password)
    result.add("@")
  result.add(u.hostname)
  if u.port.len > 0:
    result.add(":")
    result.add(u.port)
  if u.path.len > 0:
    result.add(u.path)
  if u.query.len > 0:
    result.add("?")
    result.add(u.query)
  if u.anchor.len > 0:
    result.add("#")
    result.add(u.anchor)

when isMainModule:
  block:
    let str = "http://localhost"
    let test = parseUri(str)
    doAssert test.path == ""

  block:
    let str = "http://localhost/"
    let test = parseUri(str)
    doAssert test.path == "/"

  block:
    let str = "http://localhost:8080/test"
    let test = parseUri(str)
    doAssert test.scheme == "http"
    doAssert test.port == "8080"
    doAssert test.path == "/test"
    doAssert test.hostname == "localhost"
    doAssert($test == str)

  block:
    let str = "foo://username:password@example.com:8042/over/there" &
              "/index.dtb?type=animal&name=narwhal#nose"
    let test = parseUri(str)
    doAssert test.scheme == "foo"
    doAssert test.username == "username"
    doAssert test.password == "password"
    doAssert test.hostname == "example.com"
    doAssert test.port == "8042"
    doAssert test.path == "/over/there/index.dtb"
    doAssert test.query == "type=animal&name=narwhal"
    doAssert test.anchor == "nose"
    doAssert($test == str)

  block:
    let str = "urn:example:animal:ferret:nose"
    let test = parseUri(str)
    doAssert test.scheme == "urn"
    doAssert test.path == "example:animal:ferret:nose"
    doAssert($test == str)

  block:
    let str = "mailto:username@example.com?subject=Topic"
    let test = parseUri(str)
    doAssert test.scheme == "mailto"
    doAssert test.username == "username"
    doAssert test.hostname == "example.com"
    doAssert test.query == "subject=Topic"
    doAssert($test == str)

  block:
    let str = "magnet:?xt=urn:sha1:72hsga62ba515sbd62&dn=foobar"
    let test = parseUri(str)
    doAssert test.scheme == "magnet"
    doAssert test.query == "xt=urn:sha1:72hsga62ba515sbd62&dn=foobar"
    doAssert($test == str)

  block:
    let str = "/test/foo/bar?q=2#asdf"
    let test = parseUri(str)
    doAssert test.scheme == ""
    doAssert test.path == "/test/foo/bar"
    doAssert test.query == "q=2"
    doAssert test.anchor == "asdf"
    doAssert($test == str)

  block:
    let str = "test/no/slash"
    let test = parseUri(str)
    doAssert test.path == "test/no/slash"
    doAssert($test == str)

  block:
    let str = "//git@github.com:dom96/packages"
    let test = parseUri(str)
    doAssert test.scheme == ""
    doAssert test.username == "git"
    doAssert test.hostname == "github.com"
    doAssert test.port == "dom96"
    doAssert test.path == "/packages"

  # Remove dot segments tests
  block:
    doAssert removeDotSegments("/foo/bar/baz") == "/foo/bar/baz"

  # Combine tests
  block:
    let concat = combine(parseUri("http://google.com/foo/bar/"), parseUri("baz"))
    doAssert concat.path == "/foo/bar/baz"
    doAssert concat.hostname == "google.com"
    doAssert concat.scheme == "http"

  block:
    let concat = combine(parseUri("http://google.com/foo"), parseUri("/baz"))
    doAssert concat.path == "/baz"
    doAssert concat.hostname == "google.com"
    doAssert concat.scheme == "http"

  block:
    let concat = combine(parseUri("http://google.com/foo/test"), parseUri("bar"))
    doAssert concat.path == "/foo/bar"

  block:
    let concat = combine(parseUri("http://google.com/foo/test"), parseUri("/bar"))
    doAssert concat.path == "/bar"

  block:
    let concat = combine(parseUri("http://google.com/foo/test"), parseUri("bar"))
    doAssert concat.path == "/foo/bar"

  block:
    let concat = combine(parseUri("http://google.com/foo/test/"), parseUri("bar"))
    doAssert concat.path == "/foo/test/bar"

  block:
    let concat = combine(parseUri("http://google.com/foo/test/"), parseUri("bar/"))
    doAssert concat.path == "/foo/test/bar/"

  block:
    let concat = combine(parseUri("http://google.com/foo/test/"), parseUri("bar/"),
                         parseUri("baz"))
    doAssert concat.path == "/foo/test/bar/baz"

  # `/` tests
  block:
    let test = parseUri("http://example.com/foo") / "bar/asd"
    doAssert test.path == "/foo/bar/asd"

  block:
    let test = parseUri("http://example.com/foo/") / "/bar/asd"
    doAssert test.path == "/foo/bar/asd"

  # removeDotSegments tests
  block:
    # empty test
    doAssert removeDotSegments("") == ""

  # bug #3207
  block:
    doAssert parseUri("http://qq/1").combine(parseUri("https://qqq")).`$` == "https://qqq"