* Add draft Italian stuff

lang_data/it/infix.txt

@@ -0,0 +1,3 @@
+\.\.\.
+(?<=[a-z])\.(?=[A-Z])
+(?<=[a-zA-Z])-(?=[a-zA-z])

lang_data/it/prefix.txt

@@ -0,0 +1,21 @@
+,
+"
+(
+[
+{
+*
+<
+$
+£
+“
+'
+``
+`
+#
+US$
+C$
+A$
+a-
+‘
+....
+...

lang_data/it/specials.json

@@ -0,0 +1,149 @@
+{
+"a.m.": [{"F": "a.m."}],
+"p.m.": [{"F": "p.m."}],
+
+"1a.m.": [{"F": "1"}, {"F": "a.m."}],
+"2a.m.": [{"F": "2"}, {"F": "a.m."}],
+"3a.m.": [{"F": "3"}, {"F": "a.m."}],
+"4a.m.": [{"F": "4"}, {"F": "a.m."}],
+"5a.m.": [{"F": "5"}, {"F": "a.m."}],
+"6a.m.": [{"F": "6"}, {"F": "a.m."}],
+"7a.m.": [{"F": "7"}, {"F": "a.m."}],
+"8a.m.": [{"F": "8"}, {"F": "a.m."}],
+"9a.m.": [{"F": "9"}, {"F": "a.m."}],
+"10a.m.": [{"F": "10"}, {"F": "a.m."}],
+"11a.m.": [{"F": "11"}, {"F": "a.m."}],
+"12a.m.": [{"F": "12"}, {"F": "a.m."}],
+"1am": [{"F": "1"}, {"F": "am", "L": "a.m."}],
+"2am": [{"F": "2"}, {"F": "am", "L": "a.m."}],
+"3am": [{"F": "3"}, {"F": "am", "L": "a.m."}],
+"4am": [{"F": "4"}, {"F": "am", "L": "a.m."}],
+"5am": [{"F": "5"}, {"F": "am", "L": "a.m."}],
+"6am": [{"F": "6"}, {"F": "am", "L": "a.m."}],
+"7am": [{"F": "7"}, {"F": "am", "L": "a.m."}],
+"8am": [{"F": "8"}, {"F": "am", "L": "a.m."}],
+"9am": [{"F": "9"}, {"F": "am", "L": "a.m."}],
+"10am": [{"F": "10"}, {"F": "am", "L": "a.m."}],
+"11am": [{"F": "11"}, {"F": "am", "L": "a.m."}],
+"12am": [{"F": "12"}, {"F": "am", "L": "a.m."}],
+
+
+"1p.m.": [{"F": "1"}, {"F": "p.m."}],
+"2p.m.": [{"F": "2"}, {"F": "p.m."}],
+"3p.m.": [{"F": "3"}, {"F": "p.m."}],
+"4p.m.": [{"F": "4"}, {"F": "p.m."}],
+"5p.m.": [{"F": "5"}, {"F": "p.m."}],
+"6p.m.": [{"F": "6"}, {"F": "p.m."}],
+"7p.m.": [{"F": "7"}, {"F": "p.m."}],
+"8p.m.": [{"F": "8"}, {"F": "p.m."}],
+"9p.m.": [{"F": "9"}, {"F": "p.m."}],
+"10p.m.": [{"F": "10"}, {"F": "p.m."}],
+"11p.m.": [{"F": "11"}, {"F": "p.m."}],
+"12p.m.": [{"F": "12"}, {"F": "p.m."}],
+"1pm": [{"F": "1"}, {"F": "pm", "L": "p.m."}],
+"2pm": [{"F": "2"}, {"F": "pm", "L": "p.m."}],
+"3pm": [{"F": "3"}, {"F": "pm", "L": "p.m."}],
+"4pm": [{"F": "4"}, {"F": "pm", "L": "p.m."}],
+"5pm": [{"F": "5"}, {"F": "pm", "L": "p.m."}],
+"6pm": [{"F": "6"}, {"F": "pm", "L": "p.m."}],
+"7pm": [{"F": "7"}, {"F": "pm", "L": "p.m."}],
+"8pm": [{"F": "8"}, {"F": "pm", "L": "p.m."}],
+"9pm": [{"F": "9"}, {"F": "pm", "L": "p.m."}],
+"10pm": [{"F": "10"}, {"F": "pm", "L": "p.m."}],
+"11pm": [{"F": "11"}, {"F": "pm", "L": "p.m."}],
+"12pm": [{"F": "12"}, {"F": "pm", "L": "p.m."}],
+
+"Jan.": [{"F": "Jan.", "L": "Januar"}],
+"Feb.": [{"F": "Feb.", "L": "Februar"}],
+"Mär.": [{"F": "Mär.", "L": "März"}],
+"Apr.": [{"F": "Apr.", "L": "April"}],
+"Mai.": [{"F": "Mai.", "L": "Mai"}],
+"Jun.": [{"F": "Jun.", "L": "Juni"}],
+"Jul.": [{"F": "Jul.", "L": "Juli"}],
+"Aug.": [{"F": "Aug.", "L": "August"}],
+"Sep.": [{"F": "Sep.", "L": "September"}],
+"Sept.": [{"F": "Sept.", "L": "September"}],
+"Okt.": [{"F": "Okt.", "L": "Oktober"}],
+"Nov.": [{"F": "Nov.", "L": "November"}],
+"Dez.": [{"F": "Dez.", "L": "Dezember"}],
+
+":)":  [{"F": ":)"}],
+"<3":  [{"F": "<3"}],
+";)":  [{"F": ";)"}],
+"(:":  [{"F": "(:"}],
+":(":  [{"F": ":("}],
+"-_-": [{"F": "-_-"}],
+"=)":  [{"F": "=)"}],
+":/":  [{"F": ":/"}],
+":>":  [{"F": ":>"}],
+";-)": [{"F": ";-)"}],
+":Y":  [{"F": ":Y"}],
+":P":  [{"F": ":P"}],
+":-P": [{"F": ":-P"}],
+":3":  [{"F": ":3"}],
+"=3":  [{"F": "=3"}],
+"xD":  [{"F": "xD"}],
+"^_^": [{"F": "^_^"}],
+"=]":  [{"F": "=]"}],
+"=D":  [{"F": "=D"}],
+"<333":    [{"F": "<333"}],
+":))": [{"F": ":))"}],
+":0":  [{"F": ":0"}],
+"-__-":    [{"F": "-__-"}],
+"xDD": [{"F": "xDD"}],
+"o_o": [{"F": "o_o"}],
+"o_O": [{"F": "o_O"}],
+"V_V": [{"F": "V_V"}],
+"=[[": [{"F": "=[["}],
+"<33": [{"F": "<33"}],
+";p":  [{"F": ";p"}],
+";D":  [{"F": ";D"}],
+";-p": [{"F": ";-p"}],
+";(":  [{"F": ";("}],
+":p":  [{"F": ":p"}],
+":]":  [{"F": ":]"}],
+":O":  [{"F": ":O"}],
+":-/": [{"F": ":-/"}],
+":-)": [{"F": ":-)"}],
+":(((":    [{"F": ":((("}],
+":((": [{"F": ":(("}],
+":')": [{"F": ":')"}],
+"(^_^)":   [{"F": "(^_^)"}],
+"(=":  [{"F": "(="}],
+"o.O": [{"F": "o.O"}],
+"\")": [{"F": "\")"}],
+"a.": [{"F": "a."}],
+"b.": [{"F": "b."}],
+"c.": [{"F": "c."}],
+"d.": [{"F": "d."}],
+"e.": [{"F": "e."}],
+"f.": [{"F": "f."}],
+"g.": [{"F": "g."}],
+"h.": [{"F": "h."}],
+"i.": [{"F": "i."}],
+"j.": [{"F": "j."}],
+"k.": [{"F": "k."}],
+"l.": [{"F": "l."}],
+"m.": [{"F": "m."}],
+"n.": [{"F": "n."}],
+"o.": [{"F": "o."}],
+"p.": [{"F": "p."}],
+"q.": [{"F": "q."}],
+"s.": [{"F": "s."}],
+"t.": [{"F": "t."}],
+"u.": [{"F": "u."}],
+"v.": [{"F": "v."}],
+"w.": [{"F": "w."}],
+"x.": [{"F": "x."}],
+"y.": [{"F": "y."}],
+"z.": [{"F": "z."}],
+
+"z.b.": [{"F": "z.b."}],
+"e.h.": [{"F": "I.e."}],
+"o.ä.": [{"F": "I.E."}],
+"bzw.": [{"F": "bzw."}],
+"usw.": [{"F": "usw."}],
+"\n": [{"F": "\n", "pos": "SP"}],
+"\t": [{"F": "\t", "pos": "SP"}],
+" ": [{"F": " ", "pos": "SP"}]
+}

lang_data/it/suffix.txt

@@ -0,0 +1,26 @@
+,
+\"
+\)
+\]
+\}
+\*
+\!
+\?
+%
+\$
+>
+:
+;
+'
+”
+''
+'s
+'S
+’s
+’S
+’
+\.\.
+\.\.\.
+\.\.\.\.
+(?<=[a-z0-9)\]"'%\)])\.
+(?<=[0-9])km

lang_data/it/tag_map.json

@@ -0,0 +1,44 @@
+{
+"S": {"pos": "NOUN"},
+"E":   {"pos": "ADP"},
+"RD":  {"pos": "DET"},
+"V":   {"pos": "VER"},
+"_":   {"pos": "_"},
+"A":   {"pos": "ADJ"},
+"SP":  {"pos": "PROP"},
+"FF":  {"pos": "PUNC"},
+"FS":  {"pos": "PUNC"},
+"B":   {"pos": "ADV"},
+"CC":  {"pos": "CON"},
+"FB":  {"pos": "PUNC"},
+"VA":  {"pos": "AUX"},
+"PC":  {"pos": "PRO"},
+"N":   {"pos": "NUM"},
+"RI":  {"pos": "DET"},
+"PR":  {"pos": "PRO"},
+"CS":  {"pos": "SCON"},
+"BN":  {"pos": "ADV"},
+"AP":  {"pos": "DET"},
+"VM":  {"pos": "AUX"},
+"DI":  {"pos": "DET"},
+"FC":  {"pos": "PUNC"},
+"PI":  {"pos": "PRO"},
+"DD":  {"pos": "DET"},
+"DQ":  {"pos": "DET"},
+"PQ":  {"pos": "PRO"},
+"PD":  {"pos": "PRO"},
+"NO":  {"pos": "ADJ"},
+"PE":  {"pos": "PRO"},
+"T":   {"pos": "DET"},
+"X":   {"pos": "SYM"},
+"SW":  {"pos": "X"},
+"NO":  {"pos": "PRO"},
+"I":   {"pos": "INT"},
+"X":   {"pos": "X"},
+"DR":  {"pos": "DET"},
+"EA":  {"pos": "ADP"},
+"PP":  {"pos": "PRO"},
+"X":   {"pos": "NUM"},
+"DE":  {"pos": "DET"},
+"X":   {"pos": "PAR"}
+}