From d6bcb226f66bd7a8e677f5143b832d54f7487799 Mon Sep 17 00:00:00 2001
From: Madeesh Kannan <shadeMe@users.noreply.github.com>
Date: Mon, 25 Sep 2023 18:20:30 +0200
Subject: [PATCH] Update emoji library in rule-based matcher example (#13014)
---
website/docs/usage/rule-based-matching.mdx | 58 +++++++++++-----------
1 file changed, 29 insertions(+), 29 deletions(-)
diff --git a/website/docs/usage/rule-based-matching.mdx b/website/docs/usage/rule-based-matching.mdx
index 4f54415cb..d01107ea2 100644
--- a/website/docs/usage/rule-based-matching.mdx
+++ b/website/docs/usage/rule-based-matching.mdx
@@ -850,14 +850,14 @@ negative pattern. To keep it simple, we'll either add or subtract `0.1` points
this way, the score will also reflect combinations of emoji, even positive _and_
negative ones.
-With a library like [Emojipedia](https://github.com/bcongdon/python-emojipedia),
-we can also retrieve a short description for each emoji – for example, 😍's
-official title is "Smiling Face With Heart-Eyes". Assigning it to a
+With a library like [emoji](https://github.com/carpedm20/emoji), we can also
+retrieve a short description for each emoji – for example, 😍's official title
+is "Smiling Face With Heart-Eyes". Assigning it to a
[custom attribute](/usage/processing-pipelines#custom-components-attributes) on
the emoji span will make it available as `span._.emoji_desc`.
```python
-from emojipedia import Emojipedia # Installation: pip install emojipedia
+import emoji # Installation: pip install emoji
from spacy.tokens import Span # Get the global Span object
Span.set_extension("emoji_desc", default=None) # Register the custom attribute
@@ -869,9 +869,9 @@ def label_sentiment(matcher, doc, i, matches):
elif doc.vocab.strings[match_id] == "SAD":
doc.sentiment -= 0.1 # Subtract 0.1 for negative sentiment
span = doc[start:end]
- emoji = Emojipedia.search(span[0].text) # Get data for emoji
- span._.emoji_desc = emoji.title # Assign emoji description
-
+ # Verify if it is an emoji and set the extension attribute correctly.
+ if emoji.is_emoji(span[0].text):
+ span._.emoji_desc = emoji.demojize(span[0].text, delimiters=("", ""), language=doc.lang_).replace("_", " ")
```
To label the hashtags, we can use a
@@ -1096,28 +1096,28 @@ The following operators are supported by the `DependencyMatcher`, most of which
come directly from
[Semgrex](https://nlp.stanford.edu/nlp/javadoc/javanlp/edu/stanford/nlp/semgraph/semgrex/SemgrexPattern.html):
-| Symbol | Description |
-| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
-| `A < B` | `A` is the immediate dependent of `B`. |
-| `A > B` | `A` is the immediate head of `B`. |
-| `A << B` | `A` is the dependent in a chain to `B` following dep → head paths. |
-| `A >> B` | `A` is the head in a chain to `B` following head → dep paths. |
-| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
-| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(Semgrex counterpart: `..`)_. |
-| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(Semgrex counterpart: `-`)_. |
-| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(Semgrex counterpart: `--`)_. |
-| `A $+ B` | `B` is a right 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 left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
-| `A >+ B` <Tag variant="new">3.5.1</Tag> | `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` <Tag variant="new">3.5.1</Tag> | `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`. |
-| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i`. |
-| `A <+ B` <Tag variant="new">3.5.1</Tag> | `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` <Tag variant="new">3.5.1</Tag> | `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`. |
-| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i`. |
+| Symbol | Description |
+| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
+| `A < B` | `A` is the immediate dependent of `B`. |
+| `A > B` | `A` is the immediate head of `B`. |
+| `A << B` | `A` is the dependent in a chain to `B` following dep → head paths. |
+| `A >> B` | `A` is the head in a chain to `B` following head → dep paths. |
+| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
+| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(Semgrex counterpart: `..`)_. |
+| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(Semgrex counterpart: `-`)_. |
+| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(Semgrex counterpart: `--`)_. |
+| `A $+ B` | `B` is a right 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 left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
+| `A >+ B` <Tag variant="new">3.5.1</Tag> | `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` <Tag variant="new">3.5.1</Tag> | `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`. |
+| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i`. |
+| `A <+ B` <Tag variant="new">3.5.1</Tag> | `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` <Tag variant="new">3.5.1</Tag> | `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`. |
+| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i`. |
### Designing dependency matcher patterns {id="dependencymatcher-patterns"}