bugfix: rgx_split inital tag type

DeanLight · Dec 15, 2024 · cf948b1 · cf948b1
1 parent 0c36e25
commit cf948b1
Show file tree

Hide file tree

Showing 11 changed files with 40 additions and 2 deletions.
diff --git a/nbs/callbacks/001_basic_ies.ipynb b/nbs/callbacks/001_basic_ies.ipynb
@@ -308,7 +308,7 @@
     "    try:\n",
     "        first_span = next(delim_iter)\n",
     "        if first_span.start != 0:\n",
-    "            yield(initial_tag,text[:first_span.start])\n",
+    "            yield(Span(initial_tag),text[:first_span.start])\n",
     "    except StopIteration:\n",
     "        return\n",
     "    prev_span = first_span\n",

diff --git a/spannerlib/_modidx.py b/spannerlib/_modidx.py
@@ -13,6 +13,28 @@
                                                                                                                                                                           'spannerlib/adding_inference_rules_to_term_graph.py'),
                                                                  'spannerlib.adding_inference_rules_to_term_graph.AddRulesToTermGraph.run_pass': ( 'adding_inference_rules_to_term_graph.html#addrulestotermgraph.run_pass',
                                                                                                                                                    'spannerlib/adding_inference_rules_to_term_graph.py')},
+            'spannerlib.banchmark.covid': { 'spannerlib.banchmark.covid.AggDocumentTags': ( 'banchmark/covid.html#aggdocumenttags',
+                                                                                            'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.LemmaFromList': ( 'banchmark/covid.html#lemmafromlist',
+                                                                                          'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.LemmaFromList.__call__': ( 'banchmark/covid.html#lemmafromlist.__call__',
+                                                                                                   'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.LemmaFromList.__init__': ( 'banchmark/covid.html#lemmafromlist.__init__',
+                                                                                                   'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.PosFromList': ( 'banchmark/covid.html#posfromlist',
+                                                                                        'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.PosFromList.__call__': ( 'banchmark/covid.html#posfromlist.__call__',
+                                                                                                 'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.PosFromList.__init__': ( 'banchmark/covid.html#posfromlist.__init__',
+                                                                                                 'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.agg_mention': ( 'banchmark/covid.html#agg_mention',
+                                                                                        'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.rewrite': ( 'banchmark/covid.html#rewrite',
+                                                                                    'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.rewrite_docs': ( 'banchmark/covid.html#rewrite_docs',
+                                                                                         'spannerlib/banchmark/covid.py'),
+                                            'spannerlib.banchmark.covid.split_sentence': ( 'banchmark/covid.html#split_sentence',
+                                                                                           'spannerlib/banchmark/covid.py')},
             'spannerlib.data_types': { 'spannerlib.data_types.AGGFunction': ( 'primitive_data_types.html#aggfunction',
                                                                               'spannerlib/data_types.py'),
                                        'spannerlib.data_types.FreeVar': ('primitive_data_types.html#freevar', 'spannerlib/data_types.py'),

diff --git a/spannerlib/data_types.py b/spannerlib/data_types.py
@@ -1,3 +1,5 @@
+"""data types used by the engine etc to encode rules relations etc"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/006_primitive_data_types.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/engine.py b/spannerlib/engine.py
@@ -1,3 +1,5 @@
+"""Execution spannerlog commands"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/010_engine.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/ie_func/basic.py b/spannerlib/ie_func/basic.py
@@ -93,7 +93,7 @@ def rgx_split(delim, # the delimeter pattern to split on
     try:
         first_span = next(delim_iter)
         if first_span.start != 0:
-            yield(initial_tag,text[:first_span.start])
+            yield(Span(initial_tag),text[:first_span.start])
     except StopIteration:
         return
     prev_span = first_span

diff --git a/spannerlib/ie_func/rust_spanner_regex.py b/spannerlib/ie_func/rust_spanner_regex.py
@@ -1,3 +1,5 @@
+"""This module contains implementation of regex ie functions using the rust package `enum-spanner-rs`"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbs/callbacks/04d_rust_spanner_regex.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/micro_passes.py b/spannerlib/micro_passes.py
@@ -1,3 +1,5 @@
+"""passes over the AST of a statement to do semantic checks and register state in the session object"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/020_micro_passes.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/opt.py b/spannerlib/opt.py
@@ -1,3 +1,5 @@
+"""This file contains implementation of passes that optimize the term graph structure."""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/025_query_optimizations.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/ra.py b/spannerlib/ra.py
@@ -1,3 +1,5 @@
+"""relation algebra operations and ie function calculation operations"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/008_extended_RA_operations.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/span.py b/spannerlib/span.py
@@ -1,3 +1,5 @@
+"""Span class and how to interface it with pandas"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/005_spans_and_pandas.ipynb.
 
 # %% auto 0

diff --git a/spannerlib/term_graph.py b/spannerlib/term_graph.py
@@ -1,3 +1,5 @@
+"""Term graphs that encode logic of rules as graphs over RA operators and ie function executions"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/009_term_graphs.ipynb.
 
 # %% auto 0