From b8fada79c223350c65b7891d13a3fdba7d347df7 Mon Sep 17 00:00:00 2001
From: Viginum-DataScientist-6
 <210390336+Viginum-DataScientist-6@users.noreply.github.com>
Date: Wed, 30 Jul 2025 09:25:32 +0000
Subject: [PATCH] chore: remove demoji-based emojis removal

- Also remove demoji related tests and benchmarking code.
    - This speeds up the unit tests suite.
---
 d3lta/emojis_remover.py      |  7 -----
 poetry.lock                  | 50 +-----------------------------------
 pyproject.toml               |  2 --
 tests/emojis_remover_test.py | 19 +++-----------
 4 files changed, 4 insertions(+), 74 deletions(-)

diff --git a/d3lta/emojis_remover.py b/d3lta/emojis_remover.py
index 83740a1..a41db12 100644
--- a/d3lta/emojis_remover.py
+++ b/d3lta/emojis_remover.py
@@ -3,8 +3,6 @@ from abc import ABC, abstractmethod
 from dataclasses import dataclass
 from typing import final
 
-import demoji
-
 
 @dataclass
 class EmojisRemover(ABC):
@@ -96,8 +94,3 @@ class ExplicitUnicodeBlocksEmojisRemover(EmojisRemover):
 
     def _remove_symbols_implementation(self, text: str) -> str:
         return self.SYMBOLS_REGEX.sub(r"", text)
-
-
-class DemojiEmojisRemover(EmojisRemover):
-    def _remove_symbols_implementation(self, text: str) -> str:
-        return demoji.replace(text)
diff --git a/poetry.lock b/poetry.lock
index 6ab56b7..8a8cecb 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -155,21 +155,6 @@ files = [
 ]
 markers = {main = "platform_system == \"Windows\"", dev = "sys_platform == \"win32\""}
 
-[[package]]
-name = "demoji"
-version = "1.1.0"
-description = "Accurately remove and replace emojis in text strings"
-optional = false
-python-versions = ">=3.6"
-groups = ["main"]
-files = [
-    {file = "demoji-1.1.0-py3-none-any.whl", hash = "sha256:6d3256c909aea299e97fe984f827a2a060c2a8f8bfcbafa7ec9659967c5df50f"},
-    {file = "demoji-1.1.0.tar.gz", hash = "sha256:072efaeca725e6f63ab59d83abeb55b178842538ed9256455a82ebbd055ff216"},
-]
-
-[package.extras]
-ujson = ["ujson"]
-
 [[package]]
 name = "exceptiongroup"
 version = "1.3.0"
@@ -1060,18 +1045,6 @@ files = [
     {file = "protobuf-5.29.4.tar.gz", hash = "sha256:4f1dfcd7997b31ef8f53ec82781ff434a28bf71d9102ddde14d076adcfc78c99"},
 ]
 
-[[package]]
-name = "py-cpuinfo"
-version = "9.0.0"
-description = "Get CPU info with pure Python"
-optional = false
-python-versions = "*"
-groups = ["dev"]
-files = [
-    {file = "py-cpuinfo-9.0.0.tar.gz", hash = "sha256:3cdbbf3fac90dc6f118bfd64384f309edeadd902d7c8fb17f02ffa1fc3f49690"},
-    {file = "py_cpuinfo-9.0.0-py3-none-any.whl", hash = "sha256:859625bc251f64e21f077d099d4162689c762b5d6a4c3c97553d56241c9674d5"},
-]
-
 [[package]]
 name = "pybind11"
 version = "2.13.6"
@@ -1125,27 +1098,6 @@ tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 [package.extras]
 dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
 
-[[package]]
-name = "pytest-benchmark"
-version = "5.1.0"
-description = "A ``pytest`` fixture for benchmarking code. It will group the tests into rounds that are calibrated to the chosen timer."
-optional = false
-python-versions = ">=3.9"
-groups = ["dev"]
-files = [
-    {file = "pytest-benchmark-5.1.0.tar.gz", hash = "sha256:9ea661cdc292e8231f7cd4c10b0319e56a2118e2c09d9f50e1b3d150d2aca105"},
-    {file = "pytest_benchmark-5.1.0-py3-none-any.whl", hash = "sha256:922de2dfa3033c227c96da942d1878191afa135a29485fb942e85dff1c592c89"},
-]
-
-[package.dependencies]
-py-cpuinfo = "*"
-pytest = ">=8.1"
-
-[package.extras]
-aspect = ["aspectlib"]
-elasticsearch = ["elasticsearch"]
-histogram = ["pygal", "pygaljs", "setuptools"]
-
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -1748,4 +1700,4 @@ files = [
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.10"
-content-hash = "2a469cf6cd729d58a4315152a037a242fdc09dba63fe3adfe00bbb88c3f16863"
+content-hash = "63a5c842aafa7166bcfbdd716b0d51a14f2df0827ad594e0f8d8bb3d74e7df54"
diff --git a/pyproject.toml b/pyproject.toml
index 1ab49c2..e007d86 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -7,7 +7,6 @@ authors = ["Viginum"]
 
 [tool.poetry.dependencies]
 python = "^3.10"
-demoji = "^1.1.0"
 faiss-cpu = "1.9.0.post1"
 fasttext = "0.9.3"
 gensim = "4.3.3"
@@ -25,7 +24,6 @@ optional = true
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.5"
-pytest-benchmark = "^5.1.0"
 
 [build-system]
 requires = ["setuptools", "poetry-core"]
diff --git a/tests/emojis_remover_test.py b/tests/emojis_remover_test.py
index b1fc9c2..ed67a7e 100644
--- a/tests/emojis_remover_test.py
+++ b/tests/emojis_remover_test.py
@@ -6,9 +6,6 @@ from get_unicode_emojis_list import (
     EMOJI_TESTFILE_FILENAME,
     get_all_emojis_from_latest_unicode_emojis_specification_with_download,
 )
-from pytest_benchmark.fixture import (
-    BenchmarkFixture,
-)
 
 import d3lta.emojis_remover
 
@@ -17,13 +14,6 @@ import d3lta.emojis_remover
     name="emojis_remover",
     params=[
         d3lta.emojis_remover.ExplicitUnicodeBlocksEmojisRemover,
-        pytest.param(
-            d3lta.emojis_remover.DemojiEmojisRemover,
-            marks=pytest.mark.xfail(
-                reason="`demoji`'s detection engine does not detect all emojis in the Unicode specification",
-                strict=True,
-            ),
-        ),
     ],
 )
 def fixture_emojis_remover(
@@ -108,11 +98,8 @@ In consequence whereof, the National 🏞️  Assembly 👩‍🏭👨‍🏭  r
 def test_on_text_sample(
     emojis_remover: d3lta.emojis_remover.EmojisRemover,
     sample_text_with_emojipasta: str,
-    sample_text: str,
-    benchmark: BenchmarkFixture,
+    sample_text: str
 ):
-    processed = benchmark(
-        emojis_remover.remove_symbols,
+    assert emojis_remover.remove_symbols(
         sample_text_with_emojipasta,
-    )
-    assert processed == sample_text
+    ) == sample_text