Skip to content

GitLab

Commit abb84c1c authored by Eckhart Arnold's avatar Eckhart Arnold
Browse files

sync-commit: work on MLW...

parent 82e16eb0
Show whitespace changes
Inline Side-by-side
ParserCombinators.py
View file @ abb84c1c
...@@ -1150,24 +1150,16 @@ def flatten(node): ...@@ -1150,24 +1150,16 @@ def flatten(node):
node.result = tuple(new_result) node.result = tuple(new_result)
def remove_tokens(node, tokens): def remove_tokens(node, tokens={}):
"""Reomoves any among a particular set of tokens from the immediate """Reomoves any among a particular set of tokens from the immediate
descendants of a node. descendants of a node.
""" """
if node.children: if node.children:
if tokens:
node.result = tuple(child for child in node.result node.result = tuple(child for child in node.result
if child.parser.name != TOKEN_KEYWORD or if child.parser.name != TOKEN_KEYWORD or
child.result not in tokens) child.result not in tokens)
else:
def remove_all_tokens(node):
"""Removes all tokens from the immediate descendants of a node.
:param node: the node from which children that represent tokens
shall be removed
:return: the node with all children that are tokens removed
"""
if node.children:
node.result = tuple(child for child in node.result node.result = tuple(child for child in node.result
if child.parser.name != TOKEN_KEYWORD) if child.parser.name != TOKEN_KEYWORD)
......
examples/MLW/MLW_compiler.py
View file @ abb84c1c
...@@ -100,7 +100,7 @@ class MLWGrammar(ParserHeadquarter): ...@@ -100,7 +100,7 @@ class MLWGrammar(ParserHeadquarter):
DATEI_ENDE = !/./ DATEI_ENDE = !/./
NIEMALS = /(?!.)/ NIEMALS = /(?!.)/
""" """
source_hash__ = "d7afa7bb0037ee25c0cabfa6e5a956c6" source_hash__ = "2c3456ee74172407cbe1f15e3649b41f"
parser_initialization__ = "upon instatiation" parser_initialization__ = "upon instatiation"
wsp__ = mixin_comment(whitespace=r'\s*', comment=r'#.*(?:\n|$)') wsp__ = mixin_comment(whitespace=r'\s*', comment=r'#.*(?:\n|$)')
wspL__ = wsp__ wspL__ = wsp__
...@@ -151,17 +151,26 @@ class MLWGrammar(ParserHeadquarter): ...@@ -151,17 +151,26 @@ class MLWGrammar(ParserHeadquarter):
### DON'T EDIT OR REMOVE THIS LINE ### ### DON'T EDIT OR REMOVE THIS LINE ###
def test(node):
if node.parser.name == "WORT_KLEIN":
assert False, node.as_sexpr()
node = remove_expendables(node)
node = reduce_single_child(node)
assert False, node.parser.name
return node
def test(node): def test(node):
print(node.as_sexpr()) print(node.as_sexpr())
return node
def join_strings(node, delimiter='\n'):
new_result = []
n = 0
while n < len(node.result):
nd = node.result[n]
if not nd.children:
a = n
n += 1
while n < len(node.result) and not node.result[n].children:
n += 1
nd.result = delimiter.join((r.result for r in node.result[a:n]))
new_result.append(nd)
node.result = tuple(new_result)
print(node.as_sexpr())
MLWTransTable = { MLWTransTable = {
# AST Transformations for the MLW-grammar # AST Transformations for the MLW-grammar
...@@ -174,7 +183,7 @@ MLWTransTable = { ...@@ -174,7 +183,7 @@ MLWTransTable = {
"LemmaVarianten": "LemmaVarianten":
[partial(remove_tokens, tokens={'VARIANTEN'}), flatten, [partial(remove_tokens, tokens={'VARIANTEN'}), flatten,
partial(remove_tokens, tokens={',', ';'})], partial(remove_tokens, tokens={',', ';'})],
"LVariante, LVZusatz, Schreibweise": "LVariante, LVZusatz, Schreibweise, Name":
[remove_expendables, reduce_single_child], [remove_expendables, reduce_single_child],
"SWVariante": "SWVariante":
[remove_expendables, partial(remove_tokens, tokens={':'})], [remove_expendables, partial(remove_tokens, tokens={':'})],
...@@ -197,10 +206,12 @@ MLWTransTable = { ...@@ -197,10 +206,12 @@ MLWTransTable = {
"Bedeutung": no_transformation, "Bedeutung": no_transformation,
"Bedeutungskategorie": no_transformation, "Bedeutungskategorie": no_transformation,
"Interpretamente": no_transformation, "Interpretamente": no_transformation,
"LateinischeBedeutung": no_transformation, "LateinischeBedeutung, DeutscheBedeutung":
"DeutscheBedeutung": no_transformation, [remove_expendables, remove_tokens, reduce_single_child],
"Belege": no_transformation, "Belege":
"EinBeleg": no_transformation, [flatten, remove_tokens],
"EinBeleg":
[flatten], # remove_expendables], # join_strings],
"Beleg": no_transformation, "Beleg": no_transformation,
"VerweisZiel": no_transformation, "VerweisZiel": no_transformation,
"WORT, WORT_KLEIN, WORT_GROSS, GROSSSCHRIFT": "WORT, WORT_KLEIN, WORT_GROSS, GROSSSCHRIFT":
......
examples/MLW/compile_MLW-grammar.py
View file @ abb84c1c
...@@ -21,7 +21,7 @@ limitations under the License. ...@@ -21,7 +21,7 @@ limitations under the License.
import os import os
import sys import sys
sys.path.append(os.path.abspath('../')) sys.path.append(os.path.abspath('../../'))
from ParserCombinators import run_compiler from ParserCombinators import run_compiler
errors = run_compiler("MLW.ebnf") errors = run_compiler("MLW.ebnf")
if errors: if errors:
......
examples/MLW/samples/compile_MLW-entry.py
View file @ abb84c1c
...@@ -21,7 +21,7 @@ limitations under the License. ...@@ -21,7 +21,7 @@ limitations under the License.
import os import os
import sys import sys
sys.path.append(os.path.abspath('../')) sys.path.append(os.path.abspath('../../../'))
import ParserCombinators import ParserCombinators
from ParserCombinators import run_compiler, has_source_changed from ParserCombinators import run_compiler, has_source_changed
......
examples/MLW/samples/fascitergula.xml
View file @ abb84c1c
...@@ -110,40 +110,17 @@ ...@@ -110,40 +110,17 @@
<Bedeutung> <Bedeutung>
<Interpretamente> <Interpretamente>
<LateinischeBedeutung> <LateinischeBedeutung>
<token__>
LAT
</token__>
<RegExp>
pannus, faciale, sudarium pannus, faciale, sudarium
</RegExp>
</LateinischeBedeutung> </LateinischeBedeutung>
<DeutscheBedeutung> <DeutscheBedeutung>
<token__>
DEU
</token__>
<RegExp>
Gesichts-, Schweißtuch [usu liturg.; de re v. p. 32, 63] Gesichts-, Schweißtuch [usu liturg.; de re v. p. 32, 63]
</RegExp>
</DeutscheBedeutung> </DeutscheBedeutung>
<Belege> <Belege>
<token__>
BELEGE
</token__>
<ZeroOrMore>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<RegExp> <RegExp>
Catal. thes. Germ. 28,11 (post 851) -um III. Catal. thes. Germ. 28,11 (post 851) -um III.
</RegExp> </RegExp>
</EinBeleg> </EinBeleg>
</Sequence>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<OneOrMore> <OneOrMore>
<RegExp> <RegExp>
...@@ -154,21 +131,11 @@ ...@@ -154,21 +131,11 @@
</RegExp> </RegExp>
</OneOrMore> </OneOrMore>
</EinBeleg> </EinBeleg>
</Sequence>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<RegExp> <RegExp>
Catal. thes. Germ. 18,7 "-eterculi viginti quatuor". Catal. thes. Germ. 18,7 "-eterculi viginti quatuor".
</RegExp> </RegExp>
</EinBeleg> </EinBeleg>
</Sequence>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<OneOrMore> <OneOrMore>
<RegExp> <RegExp>
...@@ -179,11 +146,6 @@ ...@@ -179,11 +146,6 @@
</RegExp> </RegExp>
</OneOrMore> </OneOrMore>
</EinBeleg> </EinBeleg>
</Sequence>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<OneOrMore> <OneOrMore>
<RegExp> <RegExp>
...@@ -205,8 +167,6 @@ ...@@ -205,8 +167,6 @@
</RegExp> </RegExp>
</Zusatz> </Zusatz>
</EinBeleg> </EinBeleg>
</Sequence>
</ZeroOrMore>
</Belege> </Belege>
</Interpretamente> </Interpretamente>
</Bedeutung> </Bedeutung>
...@@ -218,40 +178,17 @@ ...@@ -218,40 +178,17 @@
<Bedeutung> <Bedeutung>
<Interpretamente> <Interpretamente>
<LateinischeBedeutung> <LateinischeBedeutung>
<token__>
LAT
</token__>
<RegExp>
capital, rica capital, rica
</RegExp>
</LateinischeBedeutung> </LateinischeBedeutung>
<DeutscheBedeutung> <DeutscheBedeutung>
<token__>
DEU
</token__>
<RegExp>
Kopftuch Kopftuch
</RegExp>
</DeutscheBedeutung> </DeutscheBedeutung>
<Belege> <Belege>
<token__>
BELEGE
</token__>
<ZeroOrMore>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<RegExp> <RegExp>
Transl. Libor. I 32 raptis feminarum -is (fa[s]citergiis var. l.). Transl. Libor. I 32 raptis feminarum -is (fa[s]citergiis var. l.).
</RegExp> </RegExp>
</EinBeleg> </EinBeleg>
</Sequence>
<Sequence>
<token__>
*
</token__>
<EinBeleg> <EinBeleg>
<OneOrMore> <OneOrMore>
<RegExp> <RegExp>
...@@ -262,8 +199,6 @@ ...@@ -262,8 +199,6 @@
</RegExp> </RegExp>
</OneOrMore> </OneOrMore>
</EinBeleg> </EinBeleg>
</Sequence>
</ZeroOrMore>
</Belege> </Belege>
</Interpretamente> </Interpretamente>
</Bedeutung> </Bedeutung>
...@@ -274,9 +209,7 @@ ...@@ -274,9 +209,7 @@
AUTORIN AUTORIN
</token__> </token__>
<Name> <Name>
<WORT>
Weber Weber
</WORT>
</Name> </Name>
</Autorinfo> </Autorinfo>
</Artikel> </Artikel>
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment