lucy-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From nwelln...@apache.org
Subject [lucy-commits] [1/3] Upgrade StandardTokenizer to Unicode 6.3.0
Date Mon, 14 Oct 2013 19:56:05 GMT
Updated Branches:
  refs/heads/master 668e82a94 -> fdae9b57b


http://git-wip-us.apache.org/repos/asf/lucy/blob/fdae9b57/modules/unicode/ucd/WordBreakTest.json
----------------------------------------------------------------------
diff --git a/modules/unicode/ucd/WordBreakTest.json b/modules/unicode/ucd/WordBreakTest.json
index 2340c5a..0894556 100644
--- a/modules/unicode/ucd/WordBreakTest.json
+++ b/modules/unicode/ucd/WordBreakTest.json
@@ -72,11 +72,11 @@
       "words" : []
    },
    {
-      "text" : "\u0001'",
+      "text" : "\u0001.",
       "words" : []
    },
    {
-      "text" : "\u0001̈'",
+      "text" : "\u0001̈.",
       "words" : []
    },
    {
@@ -112,6 +112,34 @@
       "words" : []
    },
    {
+      "text" : "\u0001א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\u0001̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\u0001\"",
+      "words" : []
+   },
+   {
+      "text" : "\u0001̈\"",
+      "words" : []
+   },
+   {
+      "text" : "\u0001'",
+      "words" : []
+   },
+   {
+      "text" : "\u0001̈'",
+      "words" : []
+   },
+   {
       "text" : "\u0001­",
       "words" : []
    },
@@ -308,11 +336,11 @@
       "words" : []
    },
    {
-      "text" : "\r'",
+      "text" : "\r.",
       "words" : []
    },
    {
-      "text" : "\r̈'",
+      "text" : "\r̈.",
       "words" : []
    },
    {
@@ -348,6 +376,34 @@
       "words" : []
    },
    {
+      "text" : "\rא",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\r̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\r\"",
+      "words" : []
+   },
+   {
+      "text" : "\r̈\"",
+      "words" : []
+   },
+   {
+      "text" : "\r'",
+      "words" : []
+   },
+   {
+      "text" : "\r̈'",
+      "words" : []
+   },
+   {
       "text" : "\r­",
       "words" : []
    },
@@ -544,11 +600,11 @@
       "words" : []
    },
    {
-      "text" : "\n'",
+      "text" : "\n.",
       "words" : []
    },
    {
-      "text" : "\n̈'",
+      "text" : "\n̈.",
       "words" : []
    },
    {
@@ -584,6 +640,34 @@
       "words" : []
    },
    {
+      "text" : "\nא",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\n̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\n\"",
+      "words" : []
+   },
+   {
+      "text" : "\n̈\"",
+      "words" : []
+   },
+   {
+      "text" : "\n'",
+      "words" : []
+   },
+   {
+      "text" : "\n̈'",
+      "words" : []
+   },
+   {
       "text" : "\n­",
       "words" : []
    },
@@ -780,11 +864,11 @@
       "words" : []
    },
    {
-      "text" : "\u000b'",
+      "text" : "\u000b.",
       "words" : []
    },
    {
-      "text" : "\u000b̈'",
+      "text" : "\u000b̈.",
       "words" : []
    },
    {
@@ -820,6 +904,34 @@
       "words" : []
    },
    {
+      "text" : "\u000bא",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\u000b̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\u000b\"",
+      "words" : []
+   },
+   {
+      "text" : "\u000b̈\"",
+      "words" : []
+   },
+   {
+      "text" : "\u000b'",
+      "words" : []
+   },
+   {
+      "text" : "\u000b̈'",
+      "words" : []
+   },
+   {
       "text" : "\u000b­",
       "words" : []
    },
@@ -1042,13 +1154,13 @@
       ]
    },
    {
-      "text" : "〱'",
+      "text" : "〱.",
       "words" : [
          "〱"
       ]
    },
    {
-      "text" : "〱̈'",
+      "text" : "〱̈.",
       "words" : [
          "〱̈"
       ]
@@ -1092,6 +1204,44 @@
       ]
    },
    {
+      "text" : "〱א",
+      "words" : [
+         "〱",
+         "א"
+      ]
+   },
+   {
+      "text" : "〱̈א",
+      "words" : [
+         "〱̈",
+         "א"
+      ]
+   },
+   {
+      "text" : "〱\"",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "〱̈\"",
+      "words" : [
+         "〱̈"
+      ]
+   },
+   {
+      "text" : "〱'",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "〱̈'",
+      "words" : [
+         "〱̈"
+      ]
+   },
+   {
       "text" : "〱­",
       "words" : [
          "〱­"
@@ -1340,13 +1490,13 @@
       ]
    },
    {
-      "text" : "A'",
+      "text" : "A.",
       "words" : [
          "A"
       ]
    },
    {
-      "text" : "Ä'",
+      "text" : "Ä.",
       "words" : [
          "Ä"
       ]
@@ -1388,6 +1538,42 @@
       ]
    },
    {
+      "text" : "Aא",
+      "words" : [
+         "Aא"
+      ]
+   },
+   {
+      "text" : "Äא",
+      "words" : [
+         "Äא"
+      ]
+   },
+   {
+      "text" : "A\"",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "Ä\"",
+      "words" : [
+         "Ä"
+      ]
+   },
+   {
+      "text" : "A'",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "Ä'",
+      "words" : [
+         "Ä"
+      ]
+   },
+   {
       "text" : "A­",
       "words" : [
          "A­"
@@ -1592,11 +1778,11 @@
       "words" : []
    },
    {
-      "text" : ":'",
+      "text" : ":.",
       "words" : []
    },
    {
-      "text" : ":̈'",
+      "text" : ":̈.",
       "words" : []
    },
    {
@@ -1632,6 +1818,34 @@
       "words" : []
    },
    {
+      "text" : ":א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ":̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ":\"",
+      "words" : []
+   },
+   {
+      "text" : ":̈\"",
+      "words" : []
+   },
+   {
+      "text" : ":'",
+      "words" : []
+   },
+   {
+      "text" : ":̈'",
+      "words" : []
+   },
+   {
       "text" : ":­",
       "words" : []
    },
@@ -1828,11 +2042,11 @@
       "words" : []
    },
    {
-      "text" : ",'",
+      "text" : ",.",
       "words" : []
    },
    {
-      "text" : ",̈'",
+      "text" : ",̈.",
       "words" : []
    },
    {
@@ -1868,6 +2082,34 @@
       "words" : []
    },
    {
+      "text" : ",א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ",̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ",\"",
+      "words" : []
+   },
+   {
+      "text" : ",̈\"",
+      "words" : []
+   },
+   {
+      "text" : ",'",
+      "words" : []
+   },
+   {
+      "text" : ",̈'",
+      "words" : []
+   },
+   {
       "text" : ",­",
       "words" : []
    },
@@ -1992,237 +2234,265 @@
       ]
    },
    {
-      "text" : "'\u0001",
+      "text" : ".\u0001",
       "words" : []
    },
    {
-      "text" : "'̈\u0001",
+      "text" : ".̈\u0001",
       "words" : []
    },
    {
-      "text" : "'\r",
+      "text" : ".\r",
       "words" : []
    },
    {
-      "text" : "'̈\r",
+      "text" : ".̈\r",
       "words" : []
    },
    {
-      "text" : "'\n",
+      "text" : ".\n",
       "words" : []
    },
    {
-      "text" : "'̈\n",
+      "text" : ".̈\n",
       "words" : []
    },
    {
-      "text" : "'\u000b",
+      "text" : ".\u000b",
       "words" : []
    },
    {
-      "text" : "'̈\u000b",
+      "text" : ".̈\u000b",
       "words" : []
    },
    {
-      "text" : "'〱",
+      "text" : ".〱",
       "words" : [
          "〱"
       ]
    },
    {
-      "text" : "'̈〱",
+      "text" : ".̈〱",
       "words" : [
          "〱"
       ]
    },
    {
-      "text" : "'A",
+      "text" : ".A",
       "words" : [
          "A"
       ]
    },
    {
-      "text" : "'̈A",
+      "text" : ".̈A",
       "words" : [
          "A"
       ]
    },
    {
-      "text" : "':",
+      "text" : ".:",
       "words" : []
    },
    {
-      "text" : "'̈:",
+      "text" : ".̈:",
       "words" : []
    },
    {
-      "text" : "',",
+      "text" : ".,",
       "words" : []
    },
    {
-      "text" : "'̈,",
+      "text" : ".̈,",
       "words" : []
    },
    {
-      "text" : "''",
+      "text" : "..",
       "words" : []
    },
    {
-      "text" : "'̈'",
+      "text" : ".̈.",
       "words" : []
    },
    {
-      "text" : "'0",
+      "text" : ".0",
       "words" : [
          "0"
       ]
    },
    {
-      "text" : "'̈0",
+      "text" : ".̈0",
       "words" : [
          "0"
       ]
    },
    {
-      "text" : "'_",
+      "text" : "._",
       "words" : [
          "_"
       ]
    },
    {
-      "text" : "'̈_",
+      "text" : ".̈_",
       "words" : [
          "_"
       ]
    },
    {
-      "text" : "'🇦",
+      "text" : ".🇦",
       "words" : []
    },
    {
-      "text" : "'̈🇦",
+      "text" : ".̈🇦",
       "words" : []
    },
    {
-      "text" : "'­",
+      "text" : ".א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ".̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : ".\"",
       "words" : []
    },
    {
-      "text" : "'̈­",
+      "text" : ".̈\"",
       "words" : []
    },
    {
-      "text" : "'̀",
+      "text" : ".'",
       "words" : []
    },
    {
-      "text" : "'̈̀",
+      "text" : ".̈'",
       "words" : []
    },
    {
-      "text" : "'a⁠",
-      "words" : [
-         "a⁠"
-      ]
+      "text" : ".­",
+      "words" : []
    },
    {
-      "text" : "'̈a⁠",
-      "words" : [
-         "a⁠"
-      ]
+      "text" : ".̈­",
+      "words" : []
    },
    {
-      "text" : "'a:",
+      "text" : ".̀",
+      "words" : []
+   },
+   {
+      "text" : ".̈̀",
+      "words" : []
+   },
+   {
+      "text" : ".a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : ".̈a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : ".a:",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'̈a:",
+      "text" : ".̈a:",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'a'",
+      "text" : ".a'",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'̈a'",
+      "text" : ".̈a'",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'a'⁠",
+      "text" : ".a'⁠",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'̈a'⁠",
+      "text" : ".̈a'⁠",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'a,",
+      "text" : ".a,",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'̈a,",
+      "text" : ".̈a,",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "'1:",
+      "text" : ".1:",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'̈1:",
+      "text" : ".̈1:",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'1'",
+      "text" : ".1'",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'̈1'",
+      "text" : ".̈1'",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'1,",
+      "text" : ".1,",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'̈1,",
+      "text" : ".̈1,",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'1.⁠",
+      "text" : ".1.⁠",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "'̈1.⁠",
+      "text" : ".̈1.⁠",
       "words" : [
          "1"
       ]
@@ -2326,13 +2596,13 @@
       ]
    },
    {
-      "text" : "0'",
+      "text" : "0.",
       "words" : [
          "0"
       ]
    },
    {
-      "text" : "0̈'",
+      "text" : "0̈.",
       "words" : [
          "0̈"
       ]
@@ -2374,6 +2644,42 @@
       ]
    },
    {
+      "text" : "0א",
+      "words" : [
+         "0א"
+      ]
+   },
+   {
+      "text" : "0̈א",
+      "words" : [
+         "0̈א"
+      ]
+   },
+   {
+      "text" : "0\"",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "0̈\"",
+      "words" : [
+         "0̈"
+      ]
+   },
+   {
+      "text" : "0'",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "0̈'",
+      "words" : [
+         "0̈"
+      ]
+   },
+   {
       "text" : "0­",
       "words" : [
          "0­"
@@ -2602,13 +2908,13 @@
       ]
    },
    {
-      "text" : "_'",
+      "text" : "_.",
       "words" : [
          "_"
       ]
    },
    {
-      "text" : "_̈'",
+      "text" : "_̈.",
       "words" : [
          "_̈"
       ]
@@ -2650,6 +2956,42 @@
       ]
    },
    {
+      "text" : "_א",
+      "words" : [
+         "_א"
+      ]
+   },
+   {
+      "text" : "_̈א",
+      "words" : [
+         "_̈א"
+      ]
+   },
+   {
+      "text" : "_\"",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "_̈\"",
+      "words" : [
+         "_̈"
+      ]
+   },
+   {
+      "text" : "_'",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "_̈'",
+      "words" : [
+         "_̈"
+      ]
+   },
+   {
       "text" : "_­",
       "words" : [
          "_­"
@@ -2730,289 +3072,1159 @@
    {
       "text" : "_̈a,",
       "words" : [
-         "_̈a"
+         "_̈a"
+      ]
+   },
+   {
+      "text" : "_1:",
+      "words" : [
+         "_1"
+      ]
+   },
+   {
+      "text" : "_̈1:",
+      "words" : [
+         "_̈1"
+      ]
+   },
+   {
+      "text" : "_1'",
+      "words" : [
+         "_1"
+      ]
+   },
+   {
+      "text" : "_̈1'",
+      "words" : [
+         "_̈1"
+      ]
+   },
+   {
+      "text" : "_1,",
+      "words" : [
+         "_1"
+      ]
+   },
+   {
+      "text" : "_̈1,",
+      "words" : [
+         "_̈1"
+      ]
+   },
+   {
+      "text" : "_1.⁠",
+      "words" : [
+         "_1"
+      ]
+   },
+   {
+      "text" : "_̈1.⁠",
+      "words" : [
+         "_̈1"
+      ]
+   },
+   {
+      "text" : "🇦\u0001",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈\u0001",
+      "words" : []
+   },
+   {
+      "text" : "🇦\r",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈\r",
+      "words" : []
+   },
+   {
+      "text" : "🇦\n",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈\n",
+      "words" : []
+   },
+   {
+      "text" : "🇦\u000b",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈\u000b",
+      "words" : []
+   },
+   {
+      "text" : "🇦〱",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "🇦̈〱",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "🇦A",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "🇦̈A",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "🇦:",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈:",
+      "words" : []
+   },
+   {
+      "text" : "🇦,",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈,",
+      "words" : []
+   },
+   {
+      "text" : "🇦.",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈.",
+      "words" : []
+   },
+   {
+      "text" : "🇦0",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "🇦̈0",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "🇦_",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "🇦̈_",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "🇦🇦",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈🇦",
+      "words" : []
+   },
+   {
+      "text" : "🇦א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "🇦̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "🇦\"",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈\"",
+      "words" : []
+   },
+   {
+      "text" : "🇦'",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈'",
+      "words" : []
+   },
+   {
+      "text" : "🇦­",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈­",
+      "words" : []
+   },
+   {
+      "text" : "🇦̀",
+      "words" : []
+   },
+   {
+      "text" : "🇦̈̀",
+      "words" : []
+   },
+   {
+      "text" : "🇦a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "🇦̈a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "🇦a:",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦̈a:",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦a'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦̈a'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦a'⁠",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦̈a'⁠",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦a,",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦̈a,",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "🇦1:",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦̈1:",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦1'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦̈1'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦1,",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦̈1,",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦1.⁠",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "🇦̈1.⁠",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "א\u0001",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈\u0001",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א\r",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈\r",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א\n",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈\n",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א\u000b",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈\u000b",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א〱",
+      "words" : [
+         "א",
+         "〱"
+      ]
+   },
+   {
+      "text" : "א̈〱",
+      "words" : [
+         "א̈",
+         "〱"
+      ]
+   },
+   {
+      "text" : "אA",
+      "words" : [
+         "אA"
+      ]
+   },
+   {
+      "text" : "א̈A",
+      "words" : [
+         "א̈A"
+      ]
+   },
+   {
+      "text" : "א:",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈:",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א,",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈,",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א.",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈.",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א0",
+      "words" : [
+         "א0"
+      ]
+   },
+   {
+      "text" : "א̈0",
+      "words" : [
+         "א̈0"
+      ]
+   },
+   {
+      "text" : "א_",
+      "words" : [
+         "א_"
+      ]
+   },
+   {
+      "text" : "א̈_",
+      "words" : [
+         "א̈_"
+      ]
+   },
+   {
+      "text" : "א🇦",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈🇦",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "אא",
+      "words" : [
+         "אא"
+      ]
+   },
+   {
+      "text" : "א̈א",
+      "words" : [
+         "א̈א"
+      ]
+   },
+   {
+      "text" : "א\"",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "א̈\"",
+      "words" : [
+         "א̈"
+      ]
+   },
+   {
+      "text" : "א'",
+      "words" : [
+         "א'"
+      ]
+   },
+   {
+      "text" : "א̈'",
+      "words" : [
+         "א̈'"
+      ]
+   },
+   {
+      "text" : "א­",
+      "words" : [
+         "א­"
+      ]
+   },
+   {
+      "text" : "א̈­",
+      "words" : [
+         "א̈­"
+      ]
+   },
+   {
+      "text" : "א̀",
+      "words" : [
+         "א̀"
+      ]
+   },
+   {
+      "text" : "א̈̀",
+      "words" : [
+         "א̈̀"
+      ]
+   },
+   {
+      "text" : "אa⁠",
+      "words" : [
+         "אa⁠"
+      ]
+   },
+   {
+      "text" : "א̈a⁠",
+      "words" : [
+         "א̈a⁠"
+      ]
+   },
+   {
+      "text" : "אa:",
+      "words" : [
+         "אa"
+      ]
+   },
+   {
+      "text" : "א̈a:",
+      "words" : [
+         "א̈a"
+      ]
+   },
+   {
+      "text" : "אa'",
+      "words" : [
+         "אa"
+      ]
+   },
+   {
+      "text" : "א̈a'",
+      "words" : [
+         "א̈a"
+      ]
+   },
+   {
+      "text" : "אa'⁠",
+      "words" : [
+         "אa"
+      ]
+   },
+   {
+      "text" : "א̈a'⁠",
+      "words" : [
+         "א̈a"
+      ]
+   },
+   {
+      "text" : "אa,",
+      "words" : [
+         "אa"
+      ]
+   },
+   {
+      "text" : "א̈a,",
+      "words" : [
+         "א̈a"
+      ]
+   },
+   {
+      "text" : "א1:",
+      "words" : [
+         "א1"
+      ]
+   },
+   {
+      "text" : "א̈1:",
+      "words" : [
+         "א̈1"
+      ]
+   },
+   {
+      "text" : "א1'",
+      "words" : [
+         "א1"
+      ]
+   },
+   {
+      "text" : "א̈1'",
+      "words" : [
+         "א̈1"
+      ]
+   },
+   {
+      "text" : "א1,",
+      "words" : [
+         "א1"
+      ]
+   },
+   {
+      "text" : "א̈1,",
+      "words" : [
+         "א̈1"
+      ]
+   },
+   {
+      "text" : "א1.⁠",
+      "words" : [
+         "א1"
+      ]
+   },
+   {
+      "text" : "א̈1.⁠",
+      "words" : [
+         "א̈1"
+      ]
+   },
+   {
+      "text" : "\"\u0001",
+      "words" : []
+   },
+   {
+      "text" : "\"̈\u0001",
+      "words" : []
+   },
+   {
+      "text" : "\"\r",
+      "words" : []
+   },
+   {
+      "text" : "\"̈\r",
+      "words" : []
+   },
+   {
+      "text" : "\"\n",
+      "words" : []
+   },
+   {
+      "text" : "\"̈\n",
+      "words" : []
+   },
+   {
+      "text" : "\"\u000b",
+      "words" : []
+   },
+   {
+      "text" : "\"̈\u000b",
+      "words" : []
+   },
+   {
+      "text" : "\"〱",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "\"̈〱",
+      "words" : [
+         "〱"
+      ]
+   },
+   {
+      "text" : "\"A",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "\"̈A",
+      "words" : [
+         "A"
+      ]
+   },
+   {
+      "text" : "\":",
+      "words" : []
+   },
+   {
+      "text" : "\"̈:",
+      "words" : []
+   },
+   {
+      "text" : "\",",
+      "words" : []
+   },
+   {
+      "text" : "\"̈,",
+      "words" : []
+   },
+   {
+      "text" : "\".",
+      "words" : []
+   },
+   {
+      "text" : "\"̈.",
+      "words" : []
+   },
+   {
+      "text" : "\"0",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "\"̈0",
+      "words" : [
+         "0"
+      ]
+   },
+   {
+      "text" : "\"_",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "\"̈_",
+      "words" : [
+         "_"
+      ]
+   },
+   {
+      "text" : "\"🇦",
+      "words" : []
+   },
+   {
+      "text" : "\"̈🇦",
+      "words" : []
+   },
+   {
+      "text" : "\"א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\"̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "\"\"",
+      "words" : []
+   },
+   {
+      "text" : "\"̈\"",
+      "words" : []
+   },
+   {
+      "text" : "\"'",
+      "words" : []
+   },
+   {
+      "text" : "\"̈'",
+      "words" : []
+   },
+   {
+      "text" : "\"­",
+      "words" : []
+   },
+   {
+      "text" : "\"̈­",
+      "words" : []
+   },
+   {
+      "text" : "\"̀",
+      "words" : []
+   },
+   {
+      "text" : "\"̈̀",
+      "words" : []
+   },
+   {
+      "text" : "\"a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "\"̈a⁠",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "\"a:",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"̈a:",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"a'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"̈a'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"a'⁠",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"̈a'⁠",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"a,",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "\"̈a,",
+      "words" : [
+         "a"
       ]
    },
    {
-      "text" : "_1:",
+      "text" : "\"1:",
       "words" : [
-         "_1"
+         "1"
       ]
    },
    {
-      "text" : "_̈1:",
+      "text" : "\"̈1:",
       "words" : [
-         "_̈1"
+         "1"
       ]
    },
    {
-      "text" : "_1'",
+      "text" : "\"1'",
       "words" : [
-         "_1"
+         "1"
       ]
    },
    {
-      "text" : "_̈1'",
+      "text" : "\"̈1'",
       "words" : [
-         "_̈1"
+         "1"
       ]
    },
    {
-      "text" : "_1,",
+      "text" : "\"1,",
       "words" : [
-         "_1"
+         "1"
       ]
    },
    {
-      "text" : "_̈1,",
+      "text" : "\"̈1,",
       "words" : [
-         "_̈1"
+         "1"
       ]
    },
    {
-      "text" : "_1.⁠",
+      "text" : "\"1.⁠",
       "words" : [
-         "_1"
+         "1"
       ]
    },
    {
-      "text" : "_̈1.⁠",
+      "text" : "\"̈1.⁠",
       "words" : [
-         "_̈1"
+         "1"
       ]
    },
    {
-      "text" : "🇦\u0001",
+      "text" : "'\u0001",
       "words" : []
    },
    {
-      "text" : "🇦̈\u0001",
+      "text" : "'̈\u0001",
       "words" : []
    },
    {
-      "text" : "🇦\r",
+      "text" : "'\r",
       "words" : []
    },
    {
-      "text" : "🇦̈\r",
+      "text" : "'̈\r",
       "words" : []
    },
    {
-      "text" : "🇦\n",
+      "text" : "'\n",
       "words" : []
    },
    {
-      "text" : "🇦̈\n",
+      "text" : "'̈\n",
       "words" : []
    },
    {
-      "text" : "🇦\u000b",
+      "text" : "'\u000b",
       "words" : []
    },
    {
-      "text" : "🇦̈\u000b",
+      "text" : "'̈\u000b",
       "words" : []
    },
    {
-      "text" : "🇦〱",
+      "text" : "'〱",
       "words" : [
          "〱"
       ]
    },
    {
-      "text" : "🇦̈〱",
+      "text" : "'̈〱",
       "words" : [
          "〱"
       ]
    },
    {
-      "text" : "🇦A",
+      "text" : "'A",
       "words" : [
          "A"
       ]
    },
    {
-      "text" : "🇦̈A",
+      "text" : "'̈A",
       "words" : [
          "A"
       ]
    },
    {
-      "text" : "🇦:",
+      "text" : "':",
       "words" : []
    },
    {
-      "text" : "🇦̈:",
+      "text" : "'̈:",
       "words" : []
    },
    {
-      "text" : "🇦,",
+      "text" : "',",
       "words" : []
    },
    {
-      "text" : "🇦̈,",
+      "text" : "'̈,",
       "words" : []
    },
    {
-      "text" : "🇦'",
+      "text" : "'.",
       "words" : []
    },
    {
-      "text" : "🇦̈'",
+      "text" : "'̈.",
       "words" : []
    },
    {
-      "text" : "🇦0",
+      "text" : "'0",
       "words" : [
          "0"
       ]
    },
    {
-      "text" : "🇦̈0",
+      "text" : "'̈0",
       "words" : [
          "0"
       ]
    },
    {
-      "text" : "🇦_",
+      "text" : "'_",
       "words" : [
          "_"
       ]
    },
    {
-      "text" : "🇦̈_",
+      "text" : "'̈_",
       "words" : [
          "_"
       ]
    },
    {
-      "text" : "🇦🇦",
+      "text" : "'🇦",
       "words" : []
    },
    {
-      "text" : "🇦̈🇦",
+      "text" : "'̈🇦",
       "words" : []
    },
    {
-      "text" : "🇦­",
+      "text" : "'א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "'̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "'\"",
       "words" : []
    },
    {
-      "text" : "🇦̈­",
+      "text" : "'̈\"",
       "words" : []
    },
    {
-      "text" : "🇦̀",
+      "text" : "''",
       "words" : []
    },
    {
-      "text" : "🇦̈̀",
+      "text" : "'̈'",
       "words" : []
    },
    {
-      "text" : "🇦a⁠",
+      "text" : "'­",
+      "words" : []
+   },
+   {
+      "text" : "'̈­",
+      "words" : []
+   },
+   {
+      "text" : "'̀",
+      "words" : []
+   },
+   {
+      "text" : "'̈̀",
+      "words" : []
+   },
+   {
+      "text" : "'a⁠",
       "words" : [
          "a⁠"
       ]
    },
    {
-      "text" : "🇦̈a⁠",
+      "text" : "'̈a⁠",
       "words" : [
          "a⁠"
       ]
    },
    {
-      "text" : "🇦a:",
+      "text" : "'a:",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦̈a:",
+      "text" : "'̈a:",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦a'",
+      "text" : "'a'",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦̈a'",
+      "text" : "'̈a'",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦a'⁠",
+      "text" : "'a'⁠",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦̈a'⁠",
+      "text" : "'̈a'⁠",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦a,",
+      "text" : "'a,",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦̈a,",
+      "text" : "'̈a,",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "🇦1:",
+      "text" : "'1:",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦̈1:",
+      "text" : "'̈1:",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦1'",
+      "text" : "'1'",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦̈1'",
+      "text" : "'̈1'",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦1,",
+      "text" : "'1,",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦̈1,",
+      "text" : "'̈1,",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦1.⁠",
+      "text" : "'1.⁠",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "🇦̈1.⁠",
+      "text" : "'̈1.⁠",
       "words" : [
          "1"
       ]
@@ -3090,11 +4302,11 @@
       "words" : []
    },
    {
-      "text" : "­'",
+      "text" : "­.",
       "words" : []
    },
    {
-      "text" : "­̈'",
+      "text" : "­̈.",
       "words" : []
    },
    {
@@ -3130,6 +4342,34 @@
       "words" : []
    },
    {
+      "text" : "­א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "­̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "­\"",
+      "words" : []
+   },
+   {
+      "text" : "­̈\"",
+      "words" : []
+   },
+   {
+      "text" : "­'",
+      "words" : []
+   },
+   {
+      "text" : "­̈'",
+      "words" : []
+   },
+   {
       "text" : "­­",
       "words" : []
    },
@@ -3326,11 +4566,11 @@
       "words" : []
    },
    {
-      "text" : "̀'",
+      "text" : "̀.",
       "words" : []
    },
    {
-      "text" : "̀̈'",
+      "text" : "̀̈.",
       "words" : []
    },
    {
@@ -3366,6 +4606,34 @@
       "words" : []
    },
    {
+      "text" : "̀א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "̀̈א",
+      "words" : [
+         "א"
+      ]
+   },
+   {
+      "text" : "̀\"",
+      "words" : []
+   },
+   {
+      "text" : "̀̈\"",
+      "words" : []
+   },
+   {
+      "text" : "̀'",
+      "words" : []
+   },
+   {
+      "text" : "̀̈'",
+      "words" : []
+   },
+   {
       "text" : "̀­",
       "words" : []
    },
@@ -3588,13 +4856,13 @@
       ]
    },
    {
-      "text" : "a⁠'",
+      "text" : "a⁠.",
       "words" : [
          "a⁠"
       ]
    },
    {
-      "text" : "a⁠̈'",
+      "text" : "a⁠̈.",
       "words" : [
          "a⁠̈"
       ]
@@ -3636,6 +4904,42 @@
       ]
    },
    {
+      "text" : "a⁠א",
+      "words" : [
+         "a⁠א"
+      ]
+   },
+   {
+      "text" : "a⁠̈א",
+      "words" : [
+         "a⁠̈א"
+      ]
+   },
+   {
+      "text" : "a⁠\"",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "a⁠̈\"",
+      "words" : [
+         "a⁠̈"
+      ]
+   },
+   {
+      "text" : "a⁠'",
+      "words" : [
+         "a⁠"
+      ]
+   },
+   {
+      "text" : "a⁠̈'",
+      "words" : [
+         "a⁠̈"
+      ]
+   },
+   {
       "text" : "a⁠­",
       "words" : [
          "a⁠­"
@@ -3866,53 +5170,89 @@
       ]
    },
    {
-      "text" : "a:'",
+      "text" : "a:.",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a:̈.",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a:0",
+      "words" : [
+         "a",
+         "0"
+      ]
+   },
+   {
+      "text" : "a:̈0",
+      "words" : [
+         "a",
+         "0"
+      ]
+   },
+   {
+      "text" : "a:_",
+      "words" : [
+         "a",
+         "_"
+      ]
+   },
+   {
+      "text" : "a:̈_",
+      "words" : [
+         "a",
+         "_"
+      ]
+   },
+   {
+      "text" : "a:🇦",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a:̈'",
+      "text" : "a:̈🇦",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a:0",
+      "text" : "a:א",
       "words" : [
-         "a",
-         "0"
+         "a:א"
       ]
    },
    {
-      "text" : "a:̈0",
+      "text" : "a:̈א",
       "words" : [
-         "a",
-         "0"
+         "a:̈א"
       ]
    },
    {
-      "text" : "a:_",
+      "text" : "a:\"",
       "words" : [
-         "a",
-         "_"
+         "a"
       ]
    },
    {
-      "text" : "a:̈_",
+      "text" : "a:̈\"",
       "words" : [
-         "a",
-         "_"
+         "a"
       ]
    },
    {
-      "text" : "a:🇦",
+      "text" : "a:'",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a:̈🇦",
+      "text" : "a:̈'",
       "words" : [
          "a"
       ]
@@ -4156,13 +5496,13 @@
       ]
    },
    {
-      "text" : "a''",
+      "text" : "a'.",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a'̈'",
+      "text" : "a'̈.",
       "words" : [
          "a"
       ]
@@ -4208,6 +5548,42 @@
       ]
    },
    {
+      "text" : "a'א",
+      "words" : [
+         "a'א"
+      ]
+   },
+   {
+      "text" : "a'̈א",
+      "words" : [
+         "a'̈א"
+      ]
+   },
+   {
+      "text" : "a'\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a'̈\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a''",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a'̈'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
       "text" : "a'­",
       "words" : [
          "a"
@@ -4446,13 +5822,13 @@
       ]
    },
    {
-      "text" : "a'⁠'",
+      "text" : "a'⁠.",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a'⁠̈'",
+      "text" : "a'⁠̈.",
       "words" : [
          "a"
       ]
@@ -4498,6 +5874,42 @@
       ]
    },
    {
+      "text" : "a'⁠א",
+      "words" : [
+         "a'⁠א"
+      ]
+   },
+   {
+      "text" : "a'⁠̈א",
+      "words" : [
+         "a'⁠̈א"
+      ]
+   },
+   {
+      "text" : "a'⁠\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a'⁠̈\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a'⁠'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a'⁠̈'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
       "text" : "a'⁠­",
       "words" : [
          "a"
@@ -4738,13 +6150,13 @@
       ]
    },
    {
-      "text" : "a,'",
+      "text" : "a,.",
       "words" : [
          "a"
       ]
    },
    {
-      "text" : "a,̈'",
+      "text" : "a,̈.",
       "words" : [
          "a"
       ]
@@ -4790,6 +6202,44 @@
       ]
    },
    {
+      "text" : "a,א",
+      "words" : [
+         "a",
+         "א"
+      ]
+   },
+   {
+      "text" : "a,̈א",
+      "words" : [
+         "a",
+         "א"
+      ]
+   },
+   {
+      "text" : "a,\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a,̈\"",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a,'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
+      "text" : "a,̈'",
+      "words" : [
+         "a"
+      ]
+   },
+   {
       "text" : "a,­",
       "words" : [
          "a"
@@ -5040,13 +6490,13 @@
       ]
    },
    {
-      "text" : "1:'",
+      "text" : "1:.",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "1:̈'",
+      "text" : "1:̈.",
       "words" : [
          "1"
       ]
@@ -5092,6 +6542,44 @@
       ]
    },
    {
+      "text" : "1:א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1:̈א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1:\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1:̈\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1:'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1:̈'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
       "text" : "1:­",
       "words" : [
          "1"
@@ -5342,13 +6830,13 @@
       ]
    },
    {
-      "text" : "1''",
+      "text" : "1'.",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "1'̈'",
+      "text" : "1'̈.",
       "words" : [
          "1"
       ]
@@ -5392,6 +6880,44 @@
       ]
    },
    {
+      "text" : "1'א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1'̈א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1'\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1'̈\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1''",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1'̈'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
       "text" : "1'­",
       "words" : [
          "1"
@@ -5634,13 +7160,13 @@
       ]
    },
    {
-      "text" : "1,'",
+      "text" : "1,.",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "1,̈'",
+      "text" : "1,̈.",
       "words" : [
          "1"
       ]
@@ -5684,6 +7210,44 @@
       ]
    },
    {
+      "text" : "1,א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1,̈א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1,\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1,̈\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1,'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1,̈'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
       "text" : "1,­",
       "words" : [
          "1"
@@ -5926,13 +7490,13 @@
       ]
    },
    {
-      "text" : "1.⁠'",
+      "text" : "1.⁠.",
       "words" : [
          "1"
       ]
    },
    {
-      "text" : "1.⁠̈'",
+      "text" : "1.⁠̈.",
       "words" : [
          "1"
       ]
@@ -5976,6 +7540,44 @@
       ]
    },
    {
+      "text" : "1.⁠א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1.⁠̈א",
+      "words" : [
+         "1",
+         "א"
+      ]
+   },
+   {
+      "text" : "1.⁠\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1.⁠̈\"",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1.⁠'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
+      "text" : "1.⁠̈'",
+      "words" : [
+         "1"
+      ]
+   },
+   {
       "text" : "1.⁠­",
       "words" : [
          "1"


Mime
View raw message