rdf+bcp47+hxl (#41): partial refactoring; rountrip drill with expecte…

…d results

officina/999999999/0/L999999999_0.py

@@ -623,7 +623,6 @@ def bcp47_langtag_callback_hxl(
         str: return HXL attributes (without HXL hashtag)
     """
 
-
     resultatum = []
     # resultatum.append('+todo')
     resultatum.append('+i_{0}'.format(langtag_meta['language'].lower()))
@@ -2537,6 +2536,7 @@ def hxl_hashtag_to_bcp47(hashtag: str) -> str:
 
     if len(rdf_parts) > 0:
         result['_callbacks']['rdf_parts'] = rdf_parts
+        # value_prefixes = None
         for item in rdf_parts:
             if item.startswith('s_'):
                 # _subject= item.replace('s_', '').replace('_', ':')
@@ -2557,47 +2557,55 @@ def hxl_hashtag_to_bcp47(hashtag: str) -> str:
             elif item.startswith('p_'):
                 _predicate = item.replace('p_', '').replace('_', ':')
                 result['extension']['r']['rdf:predicate'].append(_predicate)
-                _predicate_key, _object, _subject= _predicate.split(':')
+                _predicate_key, _object, _subject = _predicate.split(':')
                 _bpc47_g_parts.append('p{0}-p{1}-p{2}'.format(
                     _predicate_key.upper(), _object, _subject
                 ))
 
             elif item.startswith('y_'):
                 # _cell_transformer = item.replace('y_', '').lower()
                 _cell_transformer = item[2:]
-                _tkey, _tvalue = _cell_transformer.split('_')
+                tverb, tval_1 = _cell_transformer.split('_')
                 # if _tkey == 'csvwseparator':
                 # print('oi', _tkey, _tvalue)
-                if _tkey == EXTRA_OPERATORS['GS']['hxl']:
+                if tverb.lower() == EXTRA_OPERATORS['GS']['hxl']:
                     # _cell_separator = CSVW_SEPARATORS[_tvalue]
                     decoded_separator = None
-                    if _tvalue in CSVW_SEPARATORS:
-                        decoded_separator = _tvalue
+                    if tval_1 in CSVW_SEPARATORS:
+                        decoded_separator = tval_1
                         # encoded_separator = CSVW_SEPARATORS[_tvalue]
 
                     if decoded_separator is None:
                         raise NotImplementedError(
                             '[{0}] [{1}] not implemented in <{2}>'.format(
-                                _tvalue, hashtag, CSVW_SEPARATORS
+                                tval_1, hashtag, CSVW_SEPARATORS
                             ))
 
                     # result['extension']['r']['csvw:separator'] = \
                     #     decoded_separator
                     # _predicate_key, _object = _predicate.split(':')
-                    _bpc47_g_parts.append('y{0}-y{1}'.format(
+                    _bpc47_g_parts.append('y{0}-y{1}-ynop'.format(
                         EXTRA_OPERATORS['GS']['hxl'].upper(), decoded_separator
                     ))
-                elif _tkey == 'prefix':
-                    if 'prefix' not in result['extension']['r']:
-                        result['extension']['r']['prefix'] = []
-                    result['extension']['r']['prefix'].append(_tvalue.lower())
-                    # _predicate_key, _object = _predicate.split(':')
-                    _bpc47_g_parts.append('yPREFIX-{0}'.format(
-                        _tvalue.lower()
+                elif tverb == EXTRA_OPERATORS['STX']['hxl']:
+                    # if value_prefixes is None:
+                    #     value_prefixes = []
+                    # value_prefixes.append(tval_1)
+                    _bpc47_g_parts.append('y{0}-y{1}-ynop'.format(
+                        tverb.upper(), tval_1.lower()
                     ))
                 else:
                     result['_unknown'].append('rdf_parts [{0}]'.format(item))
 
+            elif item.startswith('t_'):
+                # _cell_transformer = item.replace('y_', '').lower()
+                _cell_transformer = item[2:]
+                tverb, tval_1 = _cell_transformer.split('_')
+                # raise ValueError(item)
+                _bpc47_g_parts.append('t{0}-t{1}-ynop'.format(
+                    tverb.upper(), tval_1.lower()
+                ))
+
             elif item.startswith('o_'):
                 _object = item.replace('o_', '').replace('_', ':')
                 result['extension']['r']['rdf:object'].append(_object)

officina/999999999/1568346/bcp47-to-hxl-to-rdf.sh

@@ -124,7 +124,7 @@ test_unesco_thesaurus() {
 }
 
 #######################################
-# test_unesco_thesaurus
+# bcp47_and_hxlrdf_roundtrip item
 #
 # Globals:
 #   ROOTDIR
@@ -136,14 +136,19 @@ test_unesco_thesaurus() {
 bcp47_and_hxlrdf_roundtrip() {
   bpc47="${1-""}"
   hxlattr="${2-""}"
-  bpc47_final="${4-""}"
-  hxlattr_final="${3-""}"
+  bpc47_final="${3-""}"
+  hxlattr_final="${4-""}"
 
   hxlattr_discovered=""
   hxlattr_discovered_2nd=""
   bpc47_discovered=""
   bpc47_discovered_2nd=""
 
+  stype_blue=$(tput setaf 4)
+  stype_green=$(tput setaf 2)
+  style_red=$(tput setaf 1)
+  style_normal=$(tput sgr0)
+
   if [ -n "$bpc47" ]; then
     echo "[$bpc47] bpc47 input"
 
@@ -160,8 +165,19 @@ bcp47_and_hxlrdf_roundtrip() {
 
     bpc47_discovered_2nd=${bpc47_discovered_2nd//\"/}
     echo "[$bpc47_discovered_2nd] bpc47_discovered_2nd"
-  else
-    echo "noop bpc47"
+
+    if [ -n "$bpc47_final" ]; then
+      if [ "$bpc47_final" = "$bpc47_discovered_2nd" ]; then
+        echo "${stype_green}OK [$bpc47_final]${style_normal}"
+        # printf "$STARTCOLOR%b$ENDCOLOR" "$1";
+      else
+        echo "${style_red}FAILED [$bpc47_final]${style_normal}"
+      fi
+    else
+      echo "${stype_blue}INFO: No enforced expected result${style_normal}"
+    fi
+  # else
+  #   echo "noop bpc47"
   fi
 
   if [ -n "$hxlattr" ]; then
@@ -181,24 +197,62 @@ bcp47_and_hxlrdf_roundtrip() {
     hxlattr_discovered_2nd=${hxlattr_discovered_2nd//\"/}
     echo "[$hxlattr_discovered_2nd] hxlattr_discovered_2nd"
 
-  else
-    echo "noop hxlattr"
+    if [ -n "$hxlattr_final" ]; then
+      if [ "$hxlattr_final" = "$hxlattr_discovered_2nd" ]; then
+        echo "${stype_green}OK [$hxlattr_final]${style_normal}"
+      else
+        echo "${style_red}FAILED [$hxlattr_final]${style_normal}"
+      fi
+    else
+      echo "${stype_blue}INFO: No enforced expected result${style_normal}"
+    fi
+
+  # else
+  #   echo "noop hxlattr"
   fi
   return 0
 
 }
 
+#######################################
+# bcp47_and_hxlrdf_roundtrip item
+#
+# Globals:
+#   ROOTDIR
+# Arguments:
+#   None
+# Outputs:
+#   Test result
+#######################################
+bcp47_and_hxlrdf_roundtrip__drill() {
+  echo ""
+  echo "    test1"
+  bcp47_and_hxlrdf_roundtrip \
+    "qcc-Zxxx-r-sU2203-s2-snop" \
+    "" \
+    "qcc-Zxxx-r-sU2203-s2-snop" \
+    ""
+
+  echo ""
+  echo "    test2"
+  bcp47_and_hxlrdf_roundtrip \
+    "" \
+    "+i_qcc+is_zxxx+rdf_s_u2203_s2" \
+    "" \
+    ""
+
+  echo ""
+  echo "    test3"
+  bcp47_and_hxlrdf_roundtrip \
+    "qcc-Zxxx-r-sU2203-s2-snop-yU001D-yu007c-ynop-yU0002-yunescothes-ynop-pSKOS-pbroader-ps2-tXSD-tdatetime-tnop" \
+    "" \
+    "qcc-Zxxx-r-pSKOS-pbroader-ps2-sU2203-s2-snop-tXSD-tdatetime-ynop-yU0002-yunescothes-ynop-yU001D-yu007c-ynop" \
+    ""
+}
+
 # echo "test"
 
 # bcp47_to_hxl_to_rdf__tests
 # test_unesco_thesaurus
 
-echo ""
-echo "    test1"
-bcp47_and_hxlrdf_roundtrip "qcc-Zxxx-r-sU2203-s2-snop" ""
-echo ""
-echo "    test2"
-bcp47_and_hxlrdf_roundtrip "" "+i_qcc+is_zxxx+rdf_s_u2203_s2"
-echo ""
-echo "    test3"
-bcp47_and_hxlrdf_roundtrip "qcc-Zxxx-r-sU2203-s2-snop-yU001D-yu007c-ynop-yU0002-yunescothes-ynop-pSKOS-pbroader-ps2-tXSD-tdatetime-tnop" ""
+bcp47_and_hxlrdf_roundtrip__drill