From 9054f1b0188b94371306ff10ea851e11a0becfcf Mon Sep 17 00:00:00 2001
From: Sacha Verweij <sacha.verweij@alumni.stanford.edu>
Date: Mon, 3 Jan 2022 17:26:08 -0700
Subject: [PATCH] Lift expensive Regex construction from DateFormat method
 body.

Constructing the Regex touched in this commit can represent a
significant fraction (e.g. half or better) of the runtime of
the DateFormat method touched in this commit. To make this
DateFormat method more efficient, let's lift that Regex
construction out of that method body.
---
 stdlib/Dates/src/io.jl | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/stdlib/Dates/src/io.jl b/stdlib/Dates/src/io.jl
index 1901661fff0e24..ba0958b57f6133 100644
--- a/stdlib/Dates/src/io.jl
+++ b/stdlib/Dates/src/io.jl
@@ -332,6 +332,23 @@ const CONVERSION_TRANSLATIONS = IdDict{Type, Any}(
     Time => (Hour, Minute, Second, Millisecond, Microsecond, Nanosecond, AMPM),
 )
 
+# The `DateFormat(format, locale)` method just below consumes the following Regex.
+# Constructing this Regex is fairly expensive; doing so in the method itself can
+# consume half or better of `DateFormat(format, locale)`'s runtime. So instead we
+# construct and cache it outside the method body. Note, however, that when
+# `keys(CONVERSION_SPECIFIERS)` changes, the cached Regex must be updated accordingly;
+# hence the mutability (Ref-ness) of the cache, the helper method with which to populate
+# the cache, the cache of the hash of `keys(CONVERSION_SPECIFIERS)` (to facilitate checking
+# for changes), and the lock (to maintain consistency of these objects across threads when
+# threads simultaneously modify `CONVERSION_SPECIFIERS` and construct `DateFormat`s).
+function compute_dateformat_regex(conversion_specifiers)
+    letters = String(collect(keys(conversion_specifiers)))
+    return Regex("(?<!\\\\)([\\Q$letters\\E])\\1*")
+end
+const DATEFORMAT_REGEX_LOCK = ReentrantLock()
+const DATEFORMAT_REGEX_HASH = Ref(hash(keys(CONVERSION_SPECIFIERS)))
+const DATEFORMAT_REGEX_CACHE = Ref(compute_dateformat_regex(CONVERSION_SPECIFIERS))
+
 """
     DateFormat(format::AbstractString, locale="english") -> DateFormat
 
@@ -379,8 +396,20 @@ function DateFormat(f::AbstractString, locale::DateLocale=ENGLISH)
     prev = ()
     prev_offset = 1
 
-    letters = String(collect(keys(CONVERSION_SPECIFIERS)))
-    for m in eachmatch(Regex("(?<!\\\\)([\\Q$letters\\E])\\1*"), f)
+    # To understand this block, please see the comments attached to the definitions of
+    # DATEFORMAT_REGEX_LOCK, DATEFORMAT_REGEX_HASH, and DATEFORMAT_REGEX_CACHE.
+    lock(DATEFORMAT_REGEX_LOCK)
+    try
+        dateformat_regex_hash = hash(keys(CONVERSION_SPECIFIERS))
+        if dateformat_regex_hash != DATEFORMAT_REGEX_HASH[]
+            DATEFORMAT_REGEX_HASH[] = dateformat_regex_hash
+            DATEFORMAT_REGEX_CACHE[] = compute_dateformat_regex(CONVERSION_SPECIFIERS)
+        end
+    finally
+        unlock(DATEFORMAT_REGEX_LOCK)
+    end
+
+    for m in eachmatch(DATEFORMAT_REGEX_CACHE[], f)
         tran = replace(f[prev_offset:prevind(f, m.offset)], r"\\(.)" => s"\1")
 
         if !isempty(prev)