corpus: University of Leipzig

OneDeadKey · Nov 26, 2024 · 448c496 · 448c496
1 parent eb45a47
commit 448c496
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 27 deletions.
diff --git a/kalamine/server.py b/kalamine/server.py
@@ -82,6 +82,7 @@ def main_page(layout: KeyboardLayout, angle_mod: bool = False) -> str:
                             <option>en</option>
                             <option>en+fr</option>
                             <option>fr</option>
+                            <option value="fra_mixed-typical_2012_1M-sentences">fr (Leipzig)</option>
                         </select>
                         <label for="corpus">corpus</label>
                     </form>

diff --git a/kalamine/www/corpus/LICENSE b/kalamine/www/corpus/LICENSE
@@ -34,15 +34,14 @@ electronic works. Nearly all the individual works in the collection are in the
 public domain in the United States. If an individual work is unprotected by
 copyright law in the United States and you are located in the United States, we
 do not claim a right to prevent you from copying, distributing, performing,
-	displaying or creating derivative works based on the work as long as all
-	references to Project Gutenberg are removed. Of course, we hope that you
-	will support the Project Gutenberg-tm mission of promoting free access
-	to electronic works by freely sharing Project Gutenberg-tm works in
-	compliance with the terms of this agreement for keeping the Project
-	Gutenberg-tm name associated with the work. You can easily comply with
-	the terms of this agreement by keeping this work in the same format with
-	its attached full Project Gutenberg-tm License when you share it without
-	charge with others.
+displaying or creating derivative works based on the work as long as all
+references to Project Gutenberg are removed. Of course, we hope that you will
+support the Project Gutenberg-tm mission of promoting free access to electronic
+works by freely sharing Project Gutenberg-tm works in compliance with the terms
+of this agreement for keeping the Project Gutenberg-tm name associated with the
+work. You can easily comply with the terms of this agreement by keeping this
+work in the same format with its attached full Project Gutenberg-tm License when
+you share it without charge with others.
 
 [*] This particular work is one of the few individual works protected by
 copyright law in the United States and most of the remainder of the world,

diff --git a/kalamine/www/corpus/fra_mixed-typical_2012_1M-sentences.json b/kalamine/www/corpus/fra_mixed-typical_2012_1M-sentences.json
@@ -86,7 +86,7 @@
         "ä": 0.001,
         "=": 0.001
     },
-    "digrams": {
+    "bigrams": {
         "es": 2.5852,
         "le": 2.053,
         "on": 1.8595,
@@ -793,9 +793,7 @@
         "ln": 0.0014,
         "xy": 0.0014,
         "x?": 0.0013,
-        "â": 0.0013,
         "ml": 0.0013,
-        "": 0.0013,
         "dû": 0.0013,
         "»,": 0.0013,
         "tn": 0.0013,
@@ -873,7 +871,6 @@
         "i ": 0.0009,
         "ït": 0.0009,
         "r:": 0.0009,
-        "u": 0.0009,
         "kk": 0.0009,
         "-q": 0.0009,
         "k,": 0.0009,
@@ -939,7 +936,6 @@
         "ïc": 0.0006,
         "fp": 0.0006,
         "€.": 0.0006,
-        "e": 0.0006,
         "à ": 0.0006,
         "cg": 0.0006,
         "fm": 0.0006,
@@ -1064,7 +1060,6 @@
         "©t": 0.0004,
         "td": 0.0004,
         "jd": 0.0004,
-        "a": 0.0004,
         "œi": 0.0004,
         "x:": 0.0004,
         "dê": 0.0004,
@@ -1118,7 +1113,6 @@
         ".m": 0.0003,
         ".t": 0.0003,
         "m´": 0.0003,
-        "c": 0.0003,
         "y:": 0.0003,
         "nœ": 0.0003,
         "k!": 0.0003,
@@ -1163,7 +1157,6 @@
         "lj": 0.0003,
         "h!": 0.0003,
         "\"v": 0.0003,
-        ".": 0.0003,
         "y!": 0.0003,
         "/k": 0.0003,
         "ür": 0.0003,
@@ -1327,7 +1320,6 @@
         "ón": 0.0001,
         "b:": 0.0001,
         "nî": 0.0001,
-        "'": 0.0001,
         "jr": 0.0001,
         "zs": 0.0001,
         "'ã": 0.0001,
@@ -1434,7 +1426,6 @@
         ",p": 0.0001,
         "k'": 0.0001,
         "xq": 0.0001,
-        "n": 0.0001,
         "gã": 0.0001,
         "&p": 0.0001,
         "rď": 0.0001,
@@ -1488,7 +1479,6 @@
         "ªm": 0.0001,
         "ïw": 0.0001,
         "wf": 0.0001,
-        "ã": 0.0001,
         "\"?": 0.0001,
         "½t": 0.0001,
         "nï": 0.0001,
@@ -1556,7 +1546,6 @@
         "s": 0.0001,
         "«t": 0.0001,
         "zw": 0.0001,
-        "i": 0.0001,
         "äi": 0.0001,
         "sx": 0.0001,
         "lö": 0.0001,
@@ -1618,7 +1607,6 @@
         "vô": 0.0001,
         ",f": 0.0001,
         "är": 0.0001,
-        "h": 0.0001,
         "é": 0.0001,
         "bœ": 0.0001,
         "§a": 0.0001,
@@ -1638,7 +1626,6 @@
         "ló": 0.0001,
         "qm": 0.0001,
         "éï": 0.0001,
-        "i": 0.0001,
         ":m": 0.0001,
         "hg": 0.0001,
         "üc": 0.0001,
@@ -1692,7 +1679,6 @@
         "t(": 0.0001,
         "r": 0.0001,
         "âi": 0.0001,
-        "o": 0.0001,
         "´t": 0.0001,
         ">s": 0.0001,
         "“c": 0.0001,
@@ -1718,7 +1704,6 @@
         ":d": 0.0001,
         "lď": 0.0001,
         "m’": 0.0001,
-        "s": 0.0001,
         "l¹": 0.0001,
         ":b": 0.0001,
         "`u": 0.0001,
@@ -4864,7 +4849,6 @@
         "gyp": 0.001,
         "ww.": 0.001,
         "âgé": 0.001,
-        "â": 0.001,
         "oyo": 0.001,
         "arp": 0.001,
         "thl": 0.001,
@@ -5828,7 +5812,6 @@
         "d&r": 0.001,
         "iég": 0.001,
         "thy": 0.001,
-        "e": 0.001,
         "-hu": 0.001,
         "lch": 0.001,
         "mst": 0.001,