Merge pull request #399 from jverce/fix/emoji-parquet-path

Point to the parquet file based on module path

Author: eliasdabbas

HISTORY.rst

@@ -2,6 +2,12 @@
 Change Log - advertools
 =======================
 
+0.16.5 (2025-03-19)
+-------------------
+
+* Fixed
+    - Issue with loading parquet emoji file (issue https://github.com/eliasdabbas/advertools/issues/398)
+
 0.16.4 (2024-12-19)
 -------------------
 
@@ -124,7 +130,7 @@ Change Log - advertools
     - Allow optional trailing space in log files (contributed by @andypayne)
 
 * Fixed
-    - Replace newlines with spaces while parsing JSON-LD which was causing 
+    - Replace newlines with spaces while parsing JSON-LD which was causing
       errors in some cases.
 
 
@@ -140,7 +146,7 @@ Change Log - advertools
       parameter
 
 * Fixed
-    - Clarify that while authenticating for Twitter only ``app_key`` and 
+    - Clarify that while authenticating for Twitter only ``app_key`` and
       ``app_secret`` are required, with the option to provide ``oauth_token``
       and ``oauth_token_secret`` if/when needed.
 
@@ -210,7 +216,7 @@ Change Log - advertools
 * Changed
     - Query parameter columns in ``url_to_df`` DataFrame are now sorted by how
       full the columns are (the percentage of values that are not `NA`)
- 
+
 0.11.1 (2021-04-09)
 -------------------
 
@@ -467,7 +473,7 @@ Change Log - advertools
         feeling (+ve or -ve).
 
     - New function `word_tokenize`:
-      
+
       * Used by `word_frequency` to get tokens of
         1,2,3-word phrases (or more).
       * Split a list of text into tokens of a specified number of words each.
@@ -540,7 +546,7 @@ Change Log - advertools
 * New function `serp_youtube`
     - Query YouTube API for videos, channels, or playlists
     - Multiple queries (product of parameters) in one function call
-    - Reponse looping and merging handled, one DataFrame 
+    - Reponse looping and merging handled, one DataFrame
 * `serp_goog` return Google's original error messages
 * twitter responses with entities, get the entities extracted, each in a
   separate column
@@ -578,7 +584,7 @@ Change Log - advertools
 ------------------
 
 * New set of kw_<match-type> functions.
-* Full testing and coverage. 
+* Full testing and coverage.
 
 0.1.0 (2018-07-02)
 ------------------

advertools/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Elias Dabbas"""
 __email__ = "eliasdabbas@gmail.com"
-__version__ = "0.16.4"
+__version__ = "0.16.5"
 
 from advertools.ad_create import ad_create
 from advertools.ad_from_string import ad_from_string

advertools/emoji.py

@@ -114,9 +114,14 @@
 EMOJI = re.compile(EMOJI_RAW)
 
 
+def _emoji_df_path() -> str:
+    from os.path import join
+    return join("advertools", "pkg_data", "emoji_df.parquet")
+
+
 def _emoji_entries(emoji):
     emoji_df = pd.read_parquet(
-        "advertools/emoji_df.parquet",
+        _emoji_df_path(),
         columns=["emoji", "name", "group", "sub_group"],
         filters=[("emoji", "in", set(emoji))],
     )
@@ -262,8 +267,7 @@ def emoji_search(regex):
     5     1F537  fully-qualified     🔷  large blue diamond            Symbols     geometric
     6     1F539  fully-qualified     🔹  small blue diamond            Symbols     geometric
     """
-    emoji_df_path = adv.__path__[0] + "/emoji_df.parquet"
-    emoji_df = pd.read_parquet(emoji_df_path)
+    emoji_df = pd.read_parquet(_emoji_df_path())
     result_index = (
         emoji_df.select_dtypes("object")
         .apply(lambda series: series.astype(str).str.contains(regex, case=False))

advertools/emoji_df.parquet advertools/pkg_data/emoji_df.parquetadvertools/emoji_df.parquet renamed to advertools/pkg_data/emoji_df.parquet

@@ -1,5 +1,5 @@
 const DOCUMENTATION_OPTIONS = {
-    VERSION: '0.16.4',
+    VERSION: '0.16.5',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',
@@ -10,4 +10,4 @@ const DOCUMENTATION_OPTIONS = {
     NAVIGATION_WITH_KEYS: false,
     SHOW_SEARCH_SUMMARY: true,
     ENABLE_SEARCH_SHORTCUTS: true,
-};
+};

docs/_build/html/_static/documentation_options.js

@@ -28,18 +28,19 @@ keywords = ["seo", "marketing", "advertising", "adwords", "bingads", "search-eng
 advertools = "advertools.cli:main"
 adv = "advertools.cli:main"
 
-
 [project.urls]
 Homepage = "https://adver.tools"
 Documentation = "https://advertools.readthedocs.io"
 Repository = "https://github.com/eliasdabbas/advertools.git"
 Issues = "https://github.com/eliasdabbas/advertools/issues"
 Changelog = "https://github.com/eliasdabbas/advertools/blob/master/HISTORY.rst"
 
+[tool.flit.external-data]
+directory = "advertools/pkg_data"
+
 [tool.ruff]
 target-version = "py37"
 
-
 [tool.ruff.lint]
 # Add the `line-too-long` rule to the enforced rule set.
 extend-select = ["E501"]

pyproject.toml

@@ -1,4 +1,5 @@
 pip
+build
 wheel
 flake8
 tox

requirements_dev.txt

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.16.4
+current_version = 0.16.5
 commit = True
 tag = True
 

setup.cfg

@@ -62,6 +62,6 @@
     test_suite="tests",
     tests_require=test_requirements,
     url="https://github.com/eliasdabbas/advertools",
-    version="0.16.4",
+    version="0.16.5",
     zip_safe=False,
 )