github.io
githubpreview.dev
githubusercontent.com
gitlab.io
gitpage.si
gives
giving
gjemnes.no
gjerdrum.no
gjerstad.no
gjesdal.no
gjovik.no
gjøvik.no
gkp.pk
gl
gl.srv.us
glass
gle
gleeze.com
gliding.aero
glitch.me
gliwice.pl
global
global.prod.fastly.net
global.replit.dev
global.ssl.fastly.net
globo
glogow.pl
gloomy.jp

      },
      "italian_elision": {
        "type":         "elision",
        "articles": [
          "c", "l", "all", "dall", "dell",
          "nell", "sull", "coll", "pell",
          "gl", "agl", "dagl", "degl", "negl",
          "sugl", "un", "m", "t", "s", "v", "d"
        ]
      },
      "italian_stop": {
        "type":       "stop",
        "stopwords":  "_italian_"
      },

ca=ca\n\
ckb-iq=ckb-iq\n\
ckb_IQ=ckb-iq\n\
cs=cs\n\
da=da\n\
de=de\n\
el=el\n\
en=en\n\
en-ie=en-ie\n\
en_IE=en-ie\n\
es=es\n\
et=et\n\
eu=eu\n\
fa=fa\n\
fi=fi\n\
fr=fr\n\
gl=gl\n\
gu=gu\n\
he=he\n\
hi=hi\n\
hr=hr\n\
hu=hu\n\
hy=hy\n\
id=id\n\
it=it\n\
ja=ja\n\
ko=ko\n\
lt=lt\n\
lv=lv\n\
mk=mk\n\
ml=ml\n\
nl=nl\n\
no=no\n\
pa=pa\n\

      },
      "italian_elision": {
        "type":         "elision",
        "articles": [
          "c", "l", "all", "dall", "dell",
          "nell", "sull", "coll", "pell",
          "gl", "agl", "dagl", "degl", "negl",
          "sugl", "un", "m", "t", "s", "v", "d"
        ]
      },
      "italian_stop": {
        "type":       "stop",
        "stopwords":  "_italian_"
      },

      },
      "italian_elision": {
        "type":         "elision",
        "articles": [
          "c", "l", "all", "dall", "dell",
          "nell", "sull", "coll", "pell",
          "gl", "agl", "dagl", "degl", "negl",
          "sugl", "un", "m", "t", "s", "v", "d"
        ]
      },
      "italian_stop": {
        "type":       "stop",
        "stopwords":  "_italian_"
      },

org.gh
mil.gh

// gi : http://www.nic.gi/rules.html
gi
com.gi
ltd.gi
gov.gi
mod.gi
edu.gi
org.gi

// gl : https://www.iana.org/domains/root/db/gl.html
// http://nic.gl
gl
co.gl
com.gl
edu.gl
net.gl
org.gl

// gm : http://www.nic.gm/htmlpages%5Cgm-policy.htm
gm

// gn : http://psg.com/dns/gn/gn.txt
// Submitted by registry <******@****.***>

      },
      "italian_elision": {
        "type":         "elision",
        "articles": [
          "c", "l", "all", "dall", "dell",
          "nell", "sull", "coll", "pell",
          "gl", "agl", "dagl", "degl", "negl",
          "sugl", "un", "m", "t", "s", "v", "d"
        ]
      },
      "italian_stop": {
        "type":       "stop",
        "stopwords":  "_italian_"
      },

     * en=en<br>
     * en-ie=en-ie<br>
     * en_IE=en-ie<br>
     * es=es<br>
     * et=et<br>
     * eu=eu<br>
     * fa=fa<br>
     * fi=fi<br>
     * fr=fr<br>
     * gl=gl<br>
     * gu=gu<br>
     * he=he<br>
     * hi=hi<br>
     * hr=hr<br>
     * hu=hu<br>
     * hy=hy<br>
     * id=id<br>
     * it=it<br>
     * ja=ja<br>
     * ko=ko<br>

?t&en?rops??ude?v&og?t???a??g!.&gro?hsadtob,lenap:.nomead,,oc?saak,t&en?ikcats,?ylp.6d,??i&a?v??k!.&gro?lim?moc?su,ten?ude?vog?xx,??m!.&drp?gro?lim?mo&c?n??oc?ude?vog??pk??n!.&clp,dtl,eman?gro?hcs?i!bom??l&im?oc,?m&oc?rif,?neg,ogn,ten?ude?vog?zib:.&gl,ld,no,o&c,g,??,?aw?i!b!mulp??car?d&art?dew??h&sif?tolc??k&iv?oo&b?c???ls?n&aelc?iart??p!pohs??re&enigne?tac??t&ad?ekram?hgil?lusnoc?neg?ov?soh!.tfarcnepo,??vi&g?l???o!s??u&rehcisrev?smas?tarebsnegömrev???o&d?lb?og!.&duolc,etalsnart,???r&2n084qlj--n...

    // TODO make exception message escape non-printable characters
  }

  @Test
  fun parseDoesNotTrimOtherWhitespaceCharacters() {
    // Whitespace characters list from Google's Guava team: http://goo.gl/IcR9RD
    // line tabulation
    assertThat(parse("http://h/\u000b").encodedPath).isEqualTo("/%0B")
    // information separator 4
    assertThat(parse("http://h/\u001c").encodedPath).isEqualTo("/%1C")