From 2709c6bc614a119aa936bc0ec2358d435ec6164a Mon Sep 17 00:00:00 2001
From: Marco Gorelli <33491632+MarcoGorelli@users.noreply.github.com>
Date: Sat, 2 Nov 2024 10:23:13 +0000
Subject: [PATCH] verbose regex

---
 narwhals/_pandas_like/utils.py | 59 ++++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 10 deletions(-)

diff --git a/narwhals/_pandas_like/utils.py b/narwhals/_pandas_like/utils.py
index e1a6e7a5f..287f7f878 100644
--- a/narwhals/_pandas_like/utils.py
+++ b/narwhals/_pandas_like/utils.py
@@ -30,6 +30,51 @@
     Implementation.CUDF,
     Implementation.MODIN,
 }
+PD_DATETIME_RGX = r"""^
+    datetime64\[
+        (?P<time_unit>s|ms|us|ns)               # Match time unit: s, ms, us, or ns
+        (?:,                                    # Begin non-capturing group for optional timezone
+            \s?                                 # Optional whitespace after comma
+            (?P<time_zone>                      # Start named group for timezone
+                [a-zA-Z\/]+                     # Match timezone name, e.g., UTC, America/New_York
+                (?:                             # Begin optional non-capturing group for offset
+                    [+-]\d{2}:\d{2}             # Match offset in format +HH:MM or -HH:MM
+                )?                              # End optional offset group
+            )                                   # End time_zone group
+        )?                                      # End optional timezone group
+    \]                                          # Closing bracket
+$"""
+PATTERN_PD_DATETIME = re.compile(PD_DATETIME_RGX, re.VERBOSE)
+PA_DATETIME_RGX = r"""^
+    timestamp\[
+        (?P<time_unit>s|ms|us|ns)                 # Match time unit: s, ms, us, or ns
+        (?:,                                      # Begin non-capturing group for optional timezone
+            \s?tz=                                # Match "tz=" prefix
+            (?P<time_zone>                        # Start named group for timezone
+                [a-zA-Z\/]*                       # Match timezone name (e.g., UTC, America/New_York)
+                (?:                               # Begin optional non-capturing group for offset
+                    [+-]\d{2}:\d{2}               # Match offset in format +HH:MM or -HH:MM
+                )?                                # End optional offset group
+            )                                     # End time_zone group
+        )?                                        # End optional timezone group
+    \]                                            # Closing bracket for timestamp
+    \[pyarrow\]                                   # Literal string "[pyarrow]"
+$"""
+PATTERN_PA_DATETIME = re.compile(PA_DATETIME_RGX, re.VERBOSE)
+PD_DURATION_RGX = r"""^
+    timedelta64\[
+        (?P<time_unit>s|ms|us|ns)                 # Match time unit: s, ms, us, or ns
+    \]                                            # Closing bracket for timedelta64
+$"""
+
+PATTERN_PD_DURATION = re.compile(PD_DURATION_RGX, re.VERBOSE)
+PA_DURATION_RGX = r"""^
+    duration\[
+        (?P<time_unit>s|ms|us|ns)                 # Match time unit: s, ms, us, or ns
+    \]                                            # Closing bracket for duration
+    \[pyarrow\]                                   # Literal string "[pyarrow]"
+$"""
+PATTERN_PA_DURATION = re.compile(PA_DURATION_RGX, re.VERBOSE)
 
 
 def validate_column_comparand(index: Any, other: Any) -> Any:
@@ -223,12 +268,6 @@ def native_to_narwhals_dtype(
 ) -> DType:
     dtype = str(native_column.dtype)
 
-    pd_datetime_rgx = r"^datetime64\[(?P<time_unit>s|ms|us|ns)(?:, (?P<time_zone>[a-zA-Z\/]+(?:[+-]\d{2}:\d{2})?))?\]$"
-    pa_datetime_rgx = r"^timestamp\[(?P<time_unit>s|ms|us|ns)(?:, tz=(?P<time_zone>[a-zA-Z\/]*(?:[+-]\d{2}:\d{2})?))?\]\[pyarrow\]$"
-
-    pd_duration_rgx = r"^timedelta64\[(?P<time_unit>s|ms|us|ns)\]$"
-    pa_duration_rgx = r"^duration\[(?P<time_unit>s|ms|us|ns)\]\[pyarrow\]$"
-
     if dtype in {"int64", "Int64", "Int64[pyarrow]", "int64[pyarrow]"}:
         return dtypes.Int64()
     if dtype in {"int32", "Int32", "Int32[pyarrow]", "int32[pyarrow]"}:
@@ -267,14 +306,14 @@ def native_to_narwhals_dtype(
         return dtypes.Boolean()
     if dtype == "category" or dtype.startswith("dictionary<"):
         return dtypes.Categorical()
-    if (match_ := re.match(pd_datetime_rgx, dtype)) or (
-        match_ := re.match(pa_datetime_rgx, dtype)
+    if (match_ := PATTERN_PD_DATETIME.match(dtype)) or (
+        match_ := PATTERN_PA_DATETIME.match(dtype)
     ):
         dt_time_unit: Literal["us", "ns", "ms", "s"] = match_.group("time_unit")  # type: ignore[assignment]
         dt_time_zone: str | None = match_.group("time_zone")
         return dtypes.Datetime(dt_time_unit, dt_time_zone)
-    if (match_ := re.match(pd_duration_rgx, dtype)) or (
-        match_ := re.match(pa_duration_rgx, dtype)
+    if (match_ := PATTERN_PD_DURATION.match(dtype)) or (
+        match_ := PATTERN_PA_DURATION.match(dtype)
     ):
         du_time_unit: Literal["us", "ns", "ms", "s"] = match_.group("time_unit")  # type: ignore[assignment]
         return dtypes.Duration(du_time_unit)