good word order

ETCBC · May 10, 2023 · 4bc2ced · 4bc2ced
1 parent 71cebf8
commit 4bc2ced
Show file tree

Hide file tree

Showing 103 changed files with 6,963,440 additions and 277 deletions.
diff --git a/app/__checkout__.txt b/app/__checkout__.txt
@@ -1,2 +1,2 @@
 v0.1.1
-g304f615e89851586ff5052279f4d16d3f33261fa
+g71cebf8de3d0965d8bf54f37fdd2a9338c701833
diff --git a/app/config.yaml b/app/config.yaml
@@ -19,7 +19,7 @@ provenanceSpec:
   corpus: '{org} - {repo}{relative}'
   doi: 10.5281/zenodo.notyet
   moduleSpecs: []
-  version: 0.1.1
+  version: 0.3.0
   webBase: https://public.{org}.org/{repo}
   webHint: Show this on the website
   webLang: en
@@ -28,4 +28,6 @@ provenanceSpec:
 typeDisplay:
   sentence:
     condense: true
+  w:
+    featuresBare: word_num
 writing: grc
diff --git a/app/config_custom.yaml b/app/config_custom.yaml
@@ -1,4 +1,6 @@
 typeDisplay:
+  w:
+    featuresBare: word_num
   sentence:
     condense: true
 writing: 'grc'

diff --git a/programs/lowfat.py b/programs/lowfat.py
@@ -5,7 +5,7 @@
 from tf.core.helpers import console
 from tf.core.files import initTree, unexpanduser as ux
 
-from tf.convert.helpers import ZWSP, NEST
+from tf.convert.helpers import NEST
 
 
 def convertTaskCustom(self):
@@ -213,15 +213,15 @@ def beforeChildren(cv, cur, node, tag):
         atts = {etree.QName(k).localname: v for (k, v) in node.attrib.items()}
 
         if tag == "w":
-            atts["text"] = atts["unicode"]
-            del atts["unicode"]
+            # atts["text"] = atts["unicode"]
+            atts["text"] = node.text
 
             ref = atts["ref"]
-            (b, ch, v, w) = SPLIT_REF.split(ref)
-            atts["book"] = b
-            atts["chapter"] = ch
-            atts["verse"] = v
-            atts["word_num"] = w
+            (bRef, chRef, vRef, wRef) = SPLIT_REF.split(ref)
+            atts["book"] = bRef
+            atts["chapter"] = chRef
+            atts["verse"] = vRef
+            atts["word_num"] = wRef
             thisChapterNum = atts["chapter"]
             thisVerseNum = atts["verse"]
             if thisChapterNum != cv.get("chapter", cur["chapter"]):
@@ -246,7 +246,8 @@ def beforeChildren(cv, cur, node, tag):
                 cur["verse"] = curVerse
                 cv.feature(curVerse, verse=thisVerseNum)
 
-            s = cv.slot()
+            key = f"B{cur['bookNum']:>03}-C{chRef:>03}-V{vRef:>03}-W{wRef:>04}"
+            s = cv.slot(key=key)
             cv.feature(s, **atts)
 
         else:
@@ -291,10 +292,6 @@ def afterChildren(cv, cur, node, tag):
             if tag != "w":
                 curNode = cur["elems"].pop()
 
-                if not cv.linked(curNode):
-                    s = cv.slot()
-                    cv.feature(s, ch=ZWSP, empty=1)
-
                 cv.terminate(curNode)
 
     def afterTag(cv, cur, node, tag):
@@ -336,6 +333,8 @@ def director(cv):
         cur = {}
 
         i = 0
+        cur["bookNum"] = 0
+
         for (xmlFolder, xmlFiles) in self.getXML():
             for xmlFile in xmlFiles:
                 i += 1
@@ -350,7 +349,6 @@ def director(cv):
                     cur["elems"] = []
                     cur["chapter"] = None
                     cur["verse"] = None
-                    cur["bookNum"] = 0
                     cur["sentNum"] = 0
                     walkNode(cv, cur, root)
 

diff --git a/programs/tfFromLowfat.ipynb b/programs/tfFromLowfat.ipynb
diff --git a/report/2000-01-01/elements.txt b/report/2000-01-01/elements.txt
diff --git a/report/2000-01-01/errors.txt b/report/2000-01-01/errors.txt
diff --git a/report/2000-01-01/namespaces.txt b/report/2000-01-01/namespaces.txt
@@ -0,0 +1,6 @@
+OK  1 namespace for book             :     1x None
+OK  1 namespace for milestone        :    12x None
+OK  1 namespace for p                :     3x None
+OK  1 namespace for sentence         :     3x None
+OK  1 namespace for w                :   172x None
+OK  1 namespace for wg               :   118x None