From aac8e9c68659c0f70ab09dcf48fc047cd6f8353d Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Fri, 13 May 2022 20:40:51 +0100
Subject: [PATCH 01/12] Initial commit on the snippet-search branch

---
 snippet_search/snippet_search.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100644 snippet_search/snippet_search.py

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
new file mode 100644
index 0000000..8653420
--- /dev/null
+++ b/snippet_search/snippet_search.py
@@ -0,0 +1,26 @@
+from typing import Optional
+from discord.ext import commands
+from bot import ModmailBot
+from core import checks
+from core.models import PermissionLevel
+
+
+class SnippetSearch(commands.Cog):
+    """A plugin that provides a command for searching snippets."""
+
+    def __init__(self, bot: ModmailBot):
+        self.bot = bot
+
+    @checks.has_permissions(PermissionLevel.SUPPORTER)
+    @commands.command()
+    async def tag(self, ctx: commands.Context, *, query: Optional[str]) -> None:
+        """
+        Search for a snippet.
+        """
+        ...
+
+
+def setup(bot: ModmailBot) -> None:
+    """Add the SnippetSearch cog to the bot."""
+    bot.add_cog(SnippetSearch(bot))
+

From 3fbfa76cbb50084b2ae64539780f65aa0e3079f6 Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Fri, 13 May 2022 23:09:04 +0100
Subject: [PATCH 02/12] Make a start on snippet-search

Details to be worked out in testing. Particularly the search method and
output styling.

Co-authored-by: Etzeitet <5340057+Etzeitet@users.noreply.github.com>
---
 snippet_search/snippet_search.py | 33 +++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 8653420..8d9b174 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -1,8 +1,11 @@
 from typing import Optional
+import discord
 from discord.ext import commands
 from bot import ModmailBot
 from core import checks
 from core.models import PermissionLevel
+from core.paginator import EmbedPaginatorSession
+from core.utils import truncate, escape_code_block
 
 
 class SnippetSearch(commands.Cog):
@@ -13,14 +16,38 @@ def __init__(self, bot: ModmailBot):
 
     @checks.has_permissions(PermissionLevel.SUPPORTER)
     @commands.command()
-    async def tag(self, ctx: commands.Context, *, query: Optional[str]) -> None:
+    async def tag(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
         """
         Search for a snippet.
         """
-        ...
+        if not self.bot.snippets:
+            embed = discord.Embed(
+                color=self.bot.error_color,
+                description="You dont have any snippets at the moment.",
+            )
+            embed.set_footer(
+                text=f'Check "{self.bot.prefix}help snippet add" to add a snippet.'
+            )
+            embed.set_author(name="Snippets", icon_url=ctx.guild.icon_url)
+            return await ctx.send(embed=embed)
+
+        if query is None:
+            snippets = self.bot.snippets
+        else:
+            snippets = {k: v for k, v in self.bot.snippets if query.lower() in k}
+
+        embeds = []
+
+        for name, val in snippets.items():
+            description = f"{name}\n\n{truncate(escape_code_block(val), 2048 - 7)}"
+            embed = discord.Embed(color=self.bot.main_color, description=description)
+            embed.set_author(name="Snippets", icon_url=ctx.guild.icon_url)
+            embeds.append(embed)
+
+        session = EmbedPaginatorSession(ctx, *embeds)
+        await session.run()
 
 
 def setup(bot: ModmailBot) -> None:
     """Add the SnippetSearch cog to the bot."""
     bot.add_cog(SnippetSearch(bot))
-

From fb2c12079962abda982f9ed9731d9525532d6ee9 Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 01:24:31 +0100
Subject: [PATCH 03/12] Fix command name

---
 snippet_search/snippet_search.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 8d9b174..deec693 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -16,7 +16,7 @@ def __init__(self, bot: ModmailBot):
 
     @checks.has_permissions(PermissionLevel.SUPPORTER)
     @commands.command()
-    async def tag(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
+    async def snippetsearch(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
         """
         Search for a snippet.
         """

From e11a08b18062d714dbb29ada714653126cd5fb6a Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 01:30:49 +0100
Subject: [PATCH 04/12] Fix dict comprehension

---
 snippet_search/snippet_search.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index deec693..f9ec7e2 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -34,7 +34,11 @@ async def snippetsearch(self, ctx: commands.Context, *, query: Optional[str] = N
         if query is None:
             snippets = self.bot.snippets
         else:
-            snippets = {k: v for k, v in self.bot.snippets if query.lower() in k}
+            snippets = {
+                k: v
+                for k, v in self.bot.snippets.items()
+                if query.lower() in k
+            }
 
         embeds = []
 

From 65d0f5bbf020f8be19a90526d38def71fe117f5f Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 02:09:22 +0100
Subject: [PATCH 05/12] Mostly cosmetic changes

---
 snippet_search/snippet_search.py | 35 +++++++++++++++++---------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index f9ec7e2..9c01a3a 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -15,22 +15,11 @@ def __init__(self, bot: ModmailBot):
         self.bot = bot
 
     @checks.has_permissions(PermissionLevel.SUPPORTER)
-    @commands.command()
-    async def snippetsearch(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
+    @commands.command(name="snippetsearch")
+    async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
         """
         Search for a snippet.
         """
-        if not self.bot.snippets:
-            embed = discord.Embed(
-                color=self.bot.error_color,
-                description="You dont have any snippets at the moment.",
-            )
-            embed.set_footer(
-                text=f'Check "{self.bot.prefix}help snippet add" to add a snippet.'
-            )
-            embed.set_author(name="Snippets", icon_url=ctx.guild.icon_url)
-            return await ctx.send(embed=embed)
-
         if query is None:
             snippets = self.bot.snippets
         else:
@@ -40,12 +29,26 @@ async def snippetsearch(self, ctx: commands.Context, *, query: Optional[str] = N
                 if query.lower() in k
             }
 
+        if not snippets:
+            embed = discord.Embed(
+                description="No snippets found.",
+                color=self.bot.error_color,
+            )
+            await ctx.send(embed=embed)
+            return
+
         embeds = []
 
         for name, val in snippets.items():
-            description = f"{name}\n\n{truncate(escape_code_block(val), 2048 - 7)}"
-            embed = discord.Embed(color=self.bot.main_color, description=description)
-            embed.set_author(name="Snippets", icon_url=ctx.guild.icon_url)
+            content = truncate(escape_code_block(val), 2048 - 7)
+            embed = (
+                discord.Embed(
+                    title=f'Snippets Found ({len(snippets)})',
+                    color=self.bot.main_color,
+                )
+                .add_field(name="Name", value=f"`{name}`")
+                .add_field(name="Raw Content", value=f"```\n{content}\n```")
+            )
             embeds.append(embed)
 
         session = EmbedPaginatorSession(ctx, *embeds)

From 9b2b19f4c44b4b6d992986068db2f4015b1a61fb Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 02:10:44 +0100
Subject: [PATCH 06/12] Cosmetic change; make embed fields not inline

---
 snippet_search/snippet_search.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 9c01a3a..09c69cb 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -46,8 +46,8 @@ async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] =
                     title=f'Snippets Found ({len(snippets)})',
                     color=self.bot.main_color,
                 )
-                .add_field(name="Name", value=f"`{name}`")
-                .add_field(name="Raw Content", value=f"```\n{content}\n```")
+                .add_field(name="Name", value=f"`{name}`", inline=False)
+                .add_field(name="Raw Content", value=f"```\n{content}\n```", inline=False)
             )
             embeds.append(embed)
 

From 1f5f51dd8e09602206e0df29274b824211a0d4d1 Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 16:03:23 +0100
Subject: [PATCH 07/12] Cosmetic changes

Added a separate embed to summarise the snippet search results.
---
 snippet_search/snippet_search.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 09c69cb..8c766b3 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -24,27 +24,33 @@ async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] =
             snippets = self.bot.snippets
         else:
             snippets = {
-                k: v
-                for k, v in self.bot.snippets.items()
-                if query.lower() in k
+                name: content
+                for name, content in self.bot.snippets.items()
+                if query.lower() in name
             }
 
         if not snippets:
             embed = discord.Embed(
-                description="No snippets found.",
+                description="No matching snippets found.",
                 color=self.bot.error_color,
             )
             await ctx.send(embed=embed)
             return
 
+        result_summary_embed = discord.Embed(
+            color=self.bot.main_color,
+            title=f"{len(snippets)} Matching Snippet{'s' if len(snippets) > 1 else ''}",
+            description=', '.join(f"`{name}`" for name in snippets),
+        )
+
         embeds = []
 
-        for name, val in snippets.items():
+        for i, (name, val) in enumerate(snippets.items(), start=1):
             content = truncate(escape_code_block(val), 2048 - 7)
             embed = (
                 discord.Embed(
-                    title=f'Snippets Found ({len(snippets)})',
                     color=self.bot.main_color,
+                    title="Snippet {i}",
                 )
                 .add_field(name="Name", value=f"`{name}`", inline=False)
                 .add_field(name="Raw Content", value=f"```\n{content}\n```", inline=False)

From e611e1f11ff7a243cda83d87747ffb4e6d23a843 Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 16:11:21 +0100
Subject: [PATCH 08/12] Bug fixes

---
 snippet_search/snippet_search.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 8c766b3..2c14d88 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -43,6 +43,8 @@ async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] =
             description=', '.join(f"`{name}`" for name in snippets),
         )
 
+        await ctx.send(embed=result_summary_embed)
+
         embeds = []
 
         for i, (name, val) in enumerate(snippets.items(), start=1):
@@ -50,7 +52,7 @@ async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] =
             embed = (
                 discord.Embed(
                     color=self.bot.main_color,
-                    title="Snippet {i}",
+                    title=f"Snippet {i}",
                 )
                 .add_field(name="Name", value=f"`{name}`", inline=False)
                 .add_field(name="Raw Content", value=f"```\n{content}\n```", inline=False)

From d398f804ecb9b9dcf9f30f2946688cd774b77a0d Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 18:20:47 +0100
Subject: [PATCH 09/12] Grouping of snippets, and improvements to search
 heuristic

Snippet names which correspond to the same snippet content are now
grouped together.

Snippets are now scored as: percentage of query words in name + percentage
of query words in content.
---
 snippet_search/snippet_search.py | 96 ++++++++++++++++++++++++++------
 1 file changed, 78 insertions(+), 18 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 2c14d88..1058c0b 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -6,6 +6,46 @@
 from core.models import PermissionLevel
 from core.paginator import EmbedPaginatorSession
 from core.utils import truncate, escape_code_block
+from collections import defaultdict, Counter
+import re
+
+
+WORD_PATTERN = re.compile(r"[a-zA-Z]+")
+THRESHOLD = 1.0
+
+
+def score(query, name, content):
+    if query is None:
+        return THRESHOLD
+    return (
+        (common_word_count(query, name) + common_word_count(query, content))
+        / len(words(query))
+    )
+
+
+def words(s):
+    return WORD_PATTERN.findall(s)
+
+
+def common_word_count(s1, s2):
+    return sum(
+        (
+            Counter(map(str.casefold, words(s1)))
+            & Counter(map(str.casefold, words(s2)))
+        ).values()
+    )
+
+
+def group_snippets_by_content(snippets: dict[str, str]) -> list[tuple[set[str], str]]:
+    names_by_content = defaultdict(set)
+    for name, content in snippets.items():
+        names_by_content[content.strip()].add(name)
+    grouped_snippets = []
+    for group in names_by_content.values():
+        name, *_ = group
+        content = snippets[name]
+        grouped_snippets.append((group, content))
+    return grouped_snippets
 
 
 class SnippetSearch(commands.Cog):
@@ -16,20 +56,28 @@ def __init__(self, bot: ModmailBot):
 
     @checks.has_permissions(PermissionLevel.SUPPORTER)
     @commands.command(name="snippetsearch")
-    async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] = None) -> None:
+    async def snippet_search(
+        self, ctx: commands.Context, *, query: Optional[str] = None
+    ) -> None:
         """
         Search for a snippet.
         """
-        if query is None:
-            snippets = self.bot.snippets
-        else:
-            snippets = {
-                name: content
-                for name, content in self.bot.snippets.items()
-                if query.lower() in name
-            }
-
-        if not snippets:
+        grouped_snippets = group_snippets_by_content(self.bot.snippets)
+
+        scored_groups = []
+        for i, (names, content) in enumerate(grouped_snippets):
+            group_score = max(score(query, name, content) for name in names)
+            scored_groups.append((group_score, i, names, content))
+
+        scored_groups.sort(reverse=True)
+
+        matching_snippet_groups = [
+            (names, content)
+            for group_score, _, names, content in scored_groups
+            if group_score >= THRESHOLD
+        ]
+
+        if not matching_snippet_groups:
             embed = discord.Embed(
                 description="No matching snippets found.",
                 color=self.bot.error_color,
@@ -39,23 +87,35 @@ async def snippet_search(self, ctx: commands.Context, *, query: Optional[str] =
 
         result_summary_embed = discord.Embed(
             color=self.bot.main_color,
-            title=f"{len(snippets)} Matching Snippet{'s' if len(snippets) > 1 else ''}",
-            description=', '.join(f"`{name}`" for name in snippets),
+            title=f"Found {len(matching_snippet_groups)} Matching Snippet{'s' if len(matching_snippet_groups) > 1 else ''}:",
+            description=", ".join(
+                "/".join(f"`{name}`" for name in sorted(names))
+                for names, content in matching_snippet_groups
+            ),
         )
 
         await ctx.send(embed=result_summary_embed)
 
         embeds = []
 
-        for i, (name, val) in enumerate(snippets.items(), start=1):
-            content = truncate(escape_code_block(val), 2048 - 7)
+        for names, content in matching_snippet_groups:
+            formatted_content = (
+                f"```\n{truncate(escape_code_block(content), 2048 - 7)}\n```"
+            )
             embed = (
                 discord.Embed(
                     color=self.bot.main_color,
-                    title=f"Snippet {i}",
                 )
-                .add_field(name="Name", value=f"`{name}`", inline=False)
-                .add_field(name="Raw Content", value=f"```\n{content}\n```", inline=False)
+                .add_field(
+                    name=f"Name{'s' if len(names) > 1 else ''}",
+                    value=",".join(f"`{name}`" for name in sorted(names)),
+                    inline=False,
+                )
+                .add_field(
+                    name="Raw Content",
+                    value=formatted_content,
+                    inline=False,
+                )
             )
             embeds.append(embed)
 

From 29ebaba5bb432b5a35ef8b24f648d88459aad22a Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 18:36:04 +0100
Subject: [PATCH 10/12] Bug fix; embed field value length shortened

---
 snippet_search/snippet_search.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 1058c0b..3bc945c 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -100,7 +100,7 @@ async def snippet_search(
 
         for names, content in matching_snippet_groups:
             formatted_content = (
-                f"```\n{truncate(escape_code_block(content), 2048 - 7)}\n```"
+                f"```\n{truncate(escape_code_block(content), 1000)}\n```"
             )
             embed = (
                 discord.Embed(

From 53abbf90212f52fb3f89fbcaac26b9ca09999e24 Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sat, 14 May 2022 21:01:28 +0100
Subject: [PATCH 11/12] Fix linting issues.

---
 snippet_search/snippet_search.py | 43 ++++++++++++++++++++++++--------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index 3bc945c..bbe666f 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -1,20 +1,28 @@
+import re
+from collections import Counter, defaultdict
 from typing import Optional
+
 import discord
 from discord.ext import commands
+
 from bot import ModmailBot
 from core import checks
 from core.models import PermissionLevel
 from core.paginator import EmbedPaginatorSession
-from core.utils import truncate, escape_code_block
-from collections import defaultdict, Counter
-import re
+from core.utils import escape_code_block, truncate
 
 
 WORD_PATTERN = re.compile(r"[a-zA-Z]+")
 THRESHOLD = 1.0
 
 
-def score(query, name, content):
+def score(query: str | None, name: str, content: str) -> float:
+    """
+    Return a numerical sorting score for a snippet based on a query.
+
+    More relevant snippets have higher scores. If the query is None,
+    return a score that always meets the search inclusion threshold.
+    """
     if query is None:
         return THRESHOLD
     return (
@@ -23,11 +31,18 @@ def score(query, name, content):
     )
 
 
-def words(s):
+def words(s: str) -> list[str]:
+    """
+    Extract a list of 'words' from the given string.
+
+    A 'word' is defined by the WORD_PATTERN regex.  This is purely for
+    use by the scoring function so isn't perfect.
+    """
     return WORD_PATTERN.findall(s)
 
 
-def common_word_count(s1, s2):
+def common_word_count(s1: str, s2: str) -> int:
+    """Return the number of words in common between the two strings."""
     return sum(
         (
             Counter(map(str.casefold, words(s1)))
@@ -37,6 +52,14 @@ def common_word_count(s1, s2):
 
 
 def group_snippets_by_content(snippets: dict[str, str]) -> list[tuple[set[str], str]]:
+    """
+    Take a dictionary of snippets (in the form {name: content}) and group together snippets with the same content.
+
+    Snippet contents are stipped of leading and trailing whitespace
+    before comparison.
+
+    The result is of the form [(set_of_snippet_names, content)].
+    """
     names_by_content = defaultdict(set)
     for name, content in snippets.items():
         names_by_content[content.strip()].add(name)
@@ -59,9 +82,7 @@ def __init__(self, bot: ModmailBot):
     async def snippet_search(
         self, ctx: commands.Context, *, query: Optional[str] = None
     ) -> None:
-        """
-        Search for a snippet.
-        """
+        """Search for a snippet."""
         grouped_snippets = group_snippets_by_content(self.bot.snippets)
 
         scored_groups = []
@@ -85,9 +106,11 @@ async def snippet_search(
             await ctx.send(embed=embed)
             return
 
+        num_results = len(matching_snippet_groups)
+
         result_summary_embed = discord.Embed(
             color=self.bot.main_color,
-            title=f"Found {len(matching_snippet_groups)} Matching Snippet{'s' if len(matching_snippet_groups) > 1 else ''}:",
+            title=f"Found {num_results} Matching Snippet{'s' if num_results > 1 else ''}:",
             description=", ".join(
                 "/".join(f"`{name}`" for name in sorted(names))
                 for names, content in matching_snippet_groups

From 831c1c773a3ebeaaa0ef152e26b6b7eab59810ec Mon Sep 17 00:00:00 2001
From: LXNN <lxnn.git@gmail.com>
Date: Sun, 15 May 2022 00:56:00 +0100
Subject: [PATCH 12/12] Remove Python 3.10 typing syntax that snuck in

---
 snippet_search/snippet_search.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/snippet_search/snippet_search.py b/snippet_search/snippet_search.py
index bbe666f..59d4231 100644
--- a/snippet_search/snippet_search.py
+++ b/snippet_search/snippet_search.py
@@ -16,7 +16,7 @@
 THRESHOLD = 1.0
 
 
-def score(query: str | None, name: str, content: str) -> float:
+def score(query: Optional[str], name: str, content: str) -> float:
     """
     Return a numerical sorting score for a snippet based on a query.