From 3b9af75eeceb2fc3870a73c180832821b8fce8eb Mon Sep 17 00:00:00 2001
From: Michael Hansen <mike@rhasspy.org>
Date: Wed, 27 Apr 2022 12:36:47 -0400
Subject: [PATCH] Use byte differences for sample matching

---
 Dockerfile                     |  4 ++--
 Dockerfile.debian              |  4 ++--
 Dockerfile.debian.dockerignore |  1 +
 Dockerfile.dist                |  4 ++--
 Dockerfile.dist.dockerignore   |  1 +
 Dockerfile.dockerignore        |  1 +
 tests/samples_match.sh         | 40 ++++++++++++++++++++++++++++++++++
 7 files changed, 49 insertions(+), 6 deletions(-)
 create mode 100755 tests/samples_match.sh

diff --git a/Dockerfile b/Dockerfile
index 46dc5bb..5856586 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -92,7 +92,7 @@ COPY --from=build /home/mimic3/app/ ./
 COPY --from=build /root/.local/share/mimic3/voices/ /usr/share/mimic3/voices/
 
 # Run test
-COPY tests/apope_sample.txt tests/apope_sample_*.wav ./tests/
+COPY tests/* ./tests/
 
 # Generate sample and check
 RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav" && \
@@ -101,7 +101,7 @@ RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav
     --voice 'en_UK/apope_low' \
     < tests/apope_sample.txt \
     > tests/actual_sample.wav && \
-    diff tests/actual_sample.wav "${expected_sample}"
+    tests/samples_match.sh tests/actual_sample.wav "${expected_sample}"
 
 USER mimic3
 
diff --git a/Dockerfile.debian b/Dockerfile.debian
index 2c575c8..e57c16f 100644
--- a/Dockerfile.debian
+++ b/Dockerfile.debian
@@ -166,7 +166,7 @@ RUN --mount=type=cache,id=apt-run,target=/var/cache/apt \
     xargs apt install --yes
 
 # Run test
-COPY tests/apope_sample.txt tests/apope_sample_*.wav tests/
+COPY tests/* tests/
 
 # Generate sample and check
 RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav" && \
@@ -175,7 +175,7 @@ RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav
     --voice 'en_UK/apope_low' \
     < tests/apope_sample.txt \
     > tests/actual_sample.wav && \
-    diff tests/actual_sample.wav "${expected_sample}"
+    tests/samples_match.sh tests/actual_sample.wav "${expected_sample}"
 
 # -----------------------------------------------------------------------------
 
diff --git a/Dockerfile.debian.dockerignore b/Dockerfile.debian.dockerignore
index 25b670a..8d58c97 100644
--- a/Dockerfile.debian.dockerignore
+++ b/Dockerfile.debian.dockerignore
@@ -5,6 +5,7 @@
 !pyinstaller/mimic3-download
 !tests/apope_sample.txt
 !tests/apope_sample_*.wav
+!tests/samples_match.sh
 !voices/
 !wheels/
 
diff --git a/Dockerfile.dist b/Dockerfile.dist
index 824fe55..99b8b21 100644
--- a/Dockerfile.dist
+++ b/Dockerfile.dist
@@ -88,7 +88,7 @@ COPY voices/ /root/.local/share/mimic3/voices/
 RUN .venv/bin/mimic3-download 'en_UK/apope_low'
 
 # Run test
-COPY tests/apope_sample.txt tests/apope_sample_*.wav tests/
+COPY tests/* tests/
 
 # Generate sample and check
 RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav" && \
@@ -97,7 +97,7 @@ RUN export expected_sample="tests/apope_sample_${TARGETARCH}${TARGETVARIANT}.wav
     --voice 'en_UK/apope_low' \
     < tests/apope_sample.txt \
     > tests/actual_sample.wav && \
-    diff tests/actual_sample.wav "${expected_sample}"
+    tests/samples_match.sh tests/actual_sample.wav "${expected_sample}"
 
 # -----------------------------------------------------------------------------
 
diff --git a/Dockerfile.dist.dockerignore b/Dockerfile.dist.dockerignore
index 66a67fa..42305cc 100644
--- a/Dockerfile.dist.dockerignore
+++ b/Dockerfile.dist.dockerignore
@@ -2,6 +2,7 @@
 !build-dist.sh
 !tests/apope_sample.txt
 !tests/apope_sample_*.wav
+!tests/samples_match.sh
 !voices/
 !wheels/
 !debian/control.in.*
diff --git a/Dockerfile.dockerignore b/Dockerfile.dockerignore
index 700654b..1924534 100644
--- a/Dockerfile.dockerignore
+++ b/Dockerfile.dockerignore
@@ -2,6 +2,7 @@
 !install.sh
 !tests/apope_sample.txt
 !tests/apope_sample_*.wav
+!tests/samples_match.sh
 !voices/
 !wheels/
 !debian/control.in.*
diff --git a/tests/samples_match.sh b/tests/samples_match.sh
new file mode 100755
index 0000000..72d38fe
--- /dev/null
+++ b/tests/samples_match.sh
@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+# Copyright 2022 Mycroft AI Inc.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+# -----------------------------------------------------------------------------
+#
+# Uses cmp to compare byte differences between two samples.
+# Exits with an error if differences exceed a threshold.
+#
+set -o pipefail
+
+if [ -z "$2" ]; then
+    echo 'Usage: samples_match.sh WAV1 WAV2 [threshold]';
+    exit 1
+fi
+
+wav1="$1"
+wav2="$2"
+threshold="${3:-5000}"
+
+bytes_different="$(cmp -l "${wav1}" "${wav2}" | wc -l)"
+
+if (( ${bytes_different} > ${threshold} )); then
+    echo "Samples differ too much (${bytes_different} > ${threshold})";
+    exit 1;
+fi
+
+echo 'OK'