feat: unordered steps and trends funnels in udfs (#29802)

Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>

Author: aspicer

docker-compose.dev.yml

@@ -66,9 +66,6 @@ services:
             - '9440:9440'
             - '9009:9009'
         volumes:
-            # this new entrypoint file is to fix a bug detailed here https://github.com/ClickHouse/ClickHouse/pull/59991
-            # revert this when we upgrade clickhouse
-            - ./docker/clickhouse/entrypoint.sh:/entrypoint.sh
             - ./posthog/idl:/idl
             - ./docker/clickhouse/docker-entrypoint-initdb.d:/docker-entrypoint-initdb.d
             - ./docker/clickhouse/config.xml:/etc/clickhouse-server/config.xml

docker/clickhouse/entrypoint.sh

@@ -144,6 +144,10 @@
             <type>UInt8</type>
             <name>from_step</name>
         </argument>
+        <argument>
+            <type>UInt8</type>
+            <name>to_step</name>
+        </argument>
         <argument>
             <type>UInt8</type>
             <name>num_steps</name>
@@ -183,6 +187,10 @@
             <type>UInt8</type>
             <name>from_step</name>
         </argument>
+        <argument>
+            <type>UInt8</type>
+            <name>to_step</name>
+        </argument>
         <argument>
             <type>UInt8</type>
             <name>num_steps</name>
@@ -222,6 +230,10 @@
             <type>UInt8</type>
             <name>from_step</name>
         </argument>
+        <argument>
+            <type>UInt8</type>
+            <name>to_step</name>
+        </argument>
         <argument>
             <type>UInt8</type>
             <name>num_steps</name>
@@ -260,6 +272,10 @@
             <type>UInt8</type>
             <name>from_step</name>
         </argument>
+        <argument>
+            <type>UInt8</type>
+            <name>to_step</name>
+        </argument>
         <argument>
             <type>UInt8</type>
             <name>num_steps</name>

docker/clickhouse/user_defined_function.xml

@@ -8,6 +8,7 @@ serde = { version = "1.0.104", features = ["derive"] }
 serde_json = "1.0.48"
 itertools = "0.11"
 uuid = { version = "1.10.0", features = ["v4", "serde"] }
+ordered-float = "5.0.0"
 
 [profile.release]
 lto = true

funnel-udf/Cargo.lock

@@ -5,4 +5,4 @@ cross build --target x86_64-unknown-linux-gnu --release
 cross build --target aarch64-unknown-linux-gnu --release
 cp target/x86_64-unknown-linux-gnu/release/funnels ../posthog/user_scripts/aggregate_funnel_x86_64
 cp target/aarch64-unknown-linux-gnu/release/funnels ../posthog/user_scripts/aggregate_funnel_aarch64
-echo "Make sure to run udf_versioner.py"
+echo "Make sure to run udf_versioner.py"

funnel-udf/Cargo.toml

@@ -1,11 +1,13 @@
 mod steps;
 mod trends;
+mod unordered_steps;
+mod unordered_trends;
 
-use std::env;
 use serde::{Deserialize, Serialize};
+use std::env;
 use std::io::{self, BufRead, Write};
 
-#[derive(Clone, PartialEq, Deserialize, Serialize)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 #[serde(untagged)]
 enum PropVal {
     String(String),
@@ -30,4 +32,4 @@ fn main() {
             stdout.flush().unwrap();
         }
     }
-}
+}