#
#
#            Nim's Runtime Library
#        (c) Copyright 2010 Andreas Rumpf
#
#    See the file "copying.txt", included in this
#    distribution, for details about the copyright.
#

## This module parses an XML document and creates its XML tree representation.

import streams, parsexml, strtabs, xmltree

type
  XmlError* = object of ValueError ## Exception that is raised
                                   ## for invalid XML.
    errors*: seq[string]           ## All detected parsing errors.

proc raiseInvalidXml(errors: seq[string]) =
  var e: ref XmlError
  new(e)
  e.msg = errors[0]
  e.errors = errors
  raise e

proc addNode(father, son: XmlNode) =
  if son != nil: add(father, son)

proc parse(x: var XmlParser, errors: var seq[string]): XmlNode {.gcsafe.}

proc untilElementEnd(x: var XmlParser, result: XmlNode,
                     errors: var seq[string]) =
  while true:
    case x.kind
    of xmlElementEnd:
      if x.elementName == result.tag:
        next(x)
      else:
        errors.add(errorMsg(x, "</" & result.tag & "> expected"))
        # do not skip it here!
      break
    of xmlEof:
      errors.add(errorMsg(x, "</" & result.tag & "> expected"))
      break
    else:
      result.addNode(parse(x, errors))

proc parse(x: var XmlParser, errors: var seq[string]): XmlNode =
  case x.kind
  of xmlComment:
    result = newComment(x.charData)
    next(x)
  of xmlCharData, xmlWhitespace:
    result = newText(x.charData)
    next(x)
  of xmlPI, xmlSpecial:
    # we just ignore processing instructions for now
    next(x)
  of xmlError:
    errors.add(errorMsg(x))
    next(x)
  of xmlElementStart: ## ``<elem>``
    result = newElement(x.elementName)
    next(x)
    untilElementEnd(x, result, errors)
  of xmlElementEnd:
    errors.add(errorMsg(x, "unexpected ending tag: " & x.elementName))
  of xmlElementOpen:
    result = newElement(x.elementName)
    next(x)
    result.attrs = newStringTable()
    while true:
      case x.kind
      of xmlAttribute:
        result.attrs[x.attrKey] = x.attrValue
        next(x)
      of xmlElementClose:
        next(x)
        break
      of xmlError:
        errors.add(errorMsg(x))
        next(x)
        break
      else:
        errors.add(errorMsg(x, "'>' expected"))
        next(x)
        break
    untilElementEnd(x, result, errors)
  of xmlAttribute, xmlElementClose:
    errors.add(errorMsg(x, "<some_tag> expected"))
    next(x)
  of xmlCData:
    result = newCData(x.charData)
    next(x)
  of xmlEntity:
    ## &entity;
    result = newEntity(x.entityName)
    next(x)
  of xmlEof: discard

proc parseXml*(s: Stream, filename: string,
               errors: var seq[string]): XmlNode =
  ## Parses the XML from stream ``s`` and returns a ``XmlNode``. Every
  ## occurred parsing error is added to the ``errors`` sequence.
  var x: XmlParser
  open(x, s, filename, {reportComments})
  while true:
    x.next()
    case x.kind
    of xmlElementOpen, xmlElementStart:
      result = parse(x, errors)
      break
    of xmlComment, xmlWhitespace, xmlSpecial, xmlPI: discard # just skip it
    of xmlError:
      errors.add(errorMsg(x))
    else:
      errors.add(errorMsg(x, "<some_tag> expected"))
      break
  close(x)

proc parseXml*(s: Stream): XmlNode =
  ## Parses the XML from stream ``s`` and returns a ``XmlNode``. All parsing
  ## errors are turned into an ``XmlError`` exception.
  var errors: seq[string] = @[]
  result = parseXml(s, "unknown_xml_doc", errors)
  if errors.len > 0: raiseInvalidXml(<style>pre { 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.Str