explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-13 13:17:06 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add new REL_OPs: >+, >-, <+, and <- (#12334)

Browse Source 
* Add immediate left/right child/parent dependency relations

* Add tests for new REL_OPs: `>+`, `>-`, `<+`, and `<-`.

---------

Co-authored-by: Tan Long <tanloong@foxmail.com>
This commit is contained in:
TAN Long 2023-02-28 21:36:33 +08:00 committed by Adriane Boyd
parent 4539fbae17
commit be673462be
4 changed files with 54 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
spacy/matcher/dependencymatcher.pyx
View File

@ -82,8 +82,12 @@ cdef class DependencyMatcher:
"$-": self._imm_left_sib, "$-": self._imm_left_sib,
"$++": self._right_sib, "$++": self._right_sib,
"$--": self._left_sib, "$--": self._left_sib,
">+": self._imm_right_child,
">-": self._imm_left_child,
">++": self._right_child, ">++": self._right_child,
">--": self._left_child, ">--": self._left_child,
"<+": self._imm_right_parent,
"<-": self._imm_left_parent,
"<++": self._right_parent, "<++": self._right_parent,
"<--": self._left_parent, "<--": self._left_parent,
} }
@ -427,12 +431,34 @@ cdef class DependencyMatcher:
def _left_sib(self, doc, node): def _left_sib(self, doc, node):
return [doc[child.i] for child in doc[node].head.children if child.i < node] return [doc[child.i] for child in doc[node].head.children if child.i < node]
def _imm_right_child(self, doc, node):
for child in doc[node].children:
if child.i == node + 1:
return [doc[child.i]]
return []
def _imm_left_child(self, doc, node):
for child in doc[node].children:
if child.i == node - 1:
return [doc[child.i]]
return []
def _right_child(self, doc, node): def _right_child(self, doc, node):
return [doc[child.i] for child in doc[node].children if child.i > node] return [doc[child.i] for child in doc[node].children if child.i > node]
def _left_child(self, doc, node): def _left_child(self, doc, node):
return [doc[child.i] for child in doc[node].children if child.i < node] return [doc[child.i] for child in doc[node].children if child.i < node]
def _imm_right_parent(self, doc, node):
if doc[node].head.i == node + 1:
return [doc[node].head]
return []
def _imm_left_parent(self, doc, node):
if doc[node].head.i == node - 1:
return [doc[node].head]
return []
def _right_parent(self, doc, node): def _right_parent(self, doc, node):
if doc[node].head.i > node: if doc[node].head.i > node:
return [doc[node].head] return [doc[node].head]

16
spacy/tests/matcher/test_dependency_matcher.py
View File

@ -316,16 +316,32 @@ def test_dependency_matcher_precedence_ops(en_vocab, op, num_matches):
("the", "brown", "$--", 0), ("the", "brown", "$--", 0),
("brown", "the", "$--", 1), ("brown", "the", "$--", 1),
("brown", "brown", "$--", 0), ("brown", "brown", "$--", 0),
("over", "jumped", "<+", 0),
("quick", "fox", "<+", 0),
("the", "quick", "<+", 0),
("brown", "fox", "<+", 1),
("quick", "fox", "<++", 1), ("quick", "fox", "<++", 1),
("quick", "over", "<++", 0), ("quick", "over", "<++", 0),
("over", "jumped", "<++", 0), ("over", "jumped", "<++", 0),
("the", "fox", "<++", 2), ("the", "fox", "<++", 2),
("brown", "fox", "<-", 0),
("fox", "over", "<-", 0),
("the", "over", "<-", 0),
("over", "jumped", "<-", 1),
("brown", "fox", "<--", 0), ("brown", "fox", "<--", 0),
("fox", "jumped", "<--", 0), ("fox", "jumped", "<--", 0),
("fox", "over", "<--", 1), ("fox", "over", "<--", 1),
("fox", "brown", ">+", 0),
("over", "fox", ">+", 0),
("over", "the", ">+", 0),
("jumped", "over", ">+", 1),
("jumped", "over", ">++", 1), ("jumped", "over", ">++", 1),
("fox", "lazy", ">++", 0), ("fox", "lazy", ">++", 0),
("over", "the", ">++", 0), ("over", "the", ">++", 0),
("jumped", "over", ">-", 0),
("fox", "quick", ">-", 0),
("brown", "quick", ">-", 0),
("fox", "brown", ">-", 1),
("brown", "fox", ">--", 0), ("brown", "fox", ">--", 0),
("fox", "brown", ">--", 1), ("fox", "brown", ">--", 1),
("jumped", "fox", ">--", 1), ("jumped", "fox", ">--", 1),

4
website/docs/api/dependencymatcher.mdx
View File

@ -82,8 +82,12 @@ come directly from
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. | | `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. | | `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. | | `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i` _(not in Semgrex)_. | | `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i` _(not in Semgrex)_. | | `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i` _(not in Semgrex)_. |
| `A <+ B` | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_. | | `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_. | | `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_. |

8
website/docs/usage/rule-based-matching.mdx
View File

@ -1110,6 +1110,14 @@ come directly from
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. | | `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. | | `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. | | `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i` _(not in Semgrex)_. |
| `A <+ B` | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_. |
### Designing dependency matcher patterns {id="dependencymatcher-patterns"} ### Designing dependency matcher patterns {id="dependencymatcher-patterns"}