Add hamming exercise (#79)

config.json

@@ -90,6 +90,14 @@
         "prerequisites": [],
         "difficulty": 3
       },
+      {
+        "slug": "hamming",
+        "name": "Hamming",
+        "uuid": "69a68463-3546-45eb-9560-d4c859422cbe",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 3
+      },
       {
         "slug": "isogram",
         "name": "Isogram",

exercises/practice/hamming/.docs/instructions.md

@@ -0,0 +1,27 @@
+# Instructions
+
+Calculate the Hamming distance between two DNA strands.
+
+Your body is made up of cells that contain DNA.
+Those cells regularly wear out and need replacing, which they achieve by dividing into daughter cells.
+In fact, the average human body experiences about 10 quadrillion cell divisions in a lifetime!
+
+When cells divide, their DNA replicates too.
+Sometimes during this process mistakes happen and single pieces of DNA get encoded with the incorrect information.
+If we compare two strands of DNA and count the differences between them we can see how many mistakes occurred.
+This is known as the "Hamming distance".
+
+We read DNA using the letters C, A, G and T.
+Two strands might look like this:
+
+    GAGCCTACTAACGGGAT
+    CATCGTAATGACGGCCT
+    ^ ^ ^  ^ ^    ^^
+
+They have 7 differences, and therefore the Hamming distance is 7.
+
+The Hamming distance is useful for lots of things in science, not just biology, so it's a nice phrase to be familiar with :)
+
+## Implementation notes
+
+The Hamming distance is only defined for sequences of equal length, so an attempt to calculate it between sequences of different lengths should not work.

exercises/practice/hamming/.meta/config.json

@@ -0,0 +1,19 @@
+{
+  "authors": [
+    "keiravillekode"
+  ],
+  "files": {
+    "solution": [
+      "hamming.s"
+    ],
+    "test": [
+      "hamming_test.c"
+    ],
+    "example": [
+      ".meta/example.s"
+    ]
+  },
+  "blurb": "Calculate the Hamming difference between two DNA strands.",
+  "source": "The Calculating Point Mutations problem at Rosalind",
+  "source_url": "https://rosalind.info/problems/hamm/"
+}

exercises/practice/hamming/.meta/example.s

@@ -0,0 +1,29 @@
+.equ UNEQUAL_LENGTHS, -1
+
+.text
+.globl distance
+
+/* extern int distance(const char *strand1, const char *strand2); */
+distance:
+        mov     x2, x0
+        mov     x0, #0                  /* distance */
+
+.read:
+        ldrb    w3, [x1], #1            /* load byte, with post-increment */
+        ldrb    w4, [x2], #1            /* load byte, with post-increment */
+
+        cbz     w3, .exit               /* check for null terminator */
+        cbz     w4, .exit
+
+        cmp     w3, w4
+        cinc    x0, x0, ne              /* increment distance if characters differ */
+        b       .read
+
+.exit:
+        cmp     w3, w4
+        beq     .return
+
+        mov     x0, UNEQUAL_LENGTHS
+
+.return:
+        ret

exercises/practice/hamming/.meta/tests.toml

@@ -0,0 +1,67 @@
+# This is an auto-generated file.
+#
+# Regenerating this file via `configlet sync` will:
+# - Recreate every `description` key/value pair
+# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
+# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
+# - Preserve any other key/value pair
+#
+# As user-added comments (using the # character) will be removed when this file
+# is regenerated, comments can be added via a `comment` key.
+
+[f6dcb64f-03b0-4b60-81b1-3c9dbf47e887]
+description = "empty strands"
+
+[54681314-eee2-439a-9db0-b0636c656156]
+description = "single letter identical strands"
+
+[294479a3-a4c8-478f-8d63-6209815a827b]
+description = "single letter different strands"
+
+[9aed5f34-5693-4344-9b31-40c692fb5592]
+description = "long identical strands"
+
+[cd2273a5-c576-46c8-a52b-dee251c3e6e5]
+description = "long different strands"
+
+[919f8ef0-b767-4d1b-8516-6379d07fcb28]
+description = "disallow first strand longer"
+include = false
+
+[b9228bb1-465f-4141-b40f-1f99812de5a8]
+description = "disallow first strand longer"
+reimplements = "919f8ef0-b767-4d1b-8516-6379d07fcb28"
+
+[8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e]
+description = "disallow second strand longer"
+include = false
+
+[dab38838-26bb-4fff-acbe-3b0a9bfeba2d]
+description = "disallow second strand longer"
+reimplements = "8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e"
+
+[5dce058b-28d4-4ca7-aa64-adfe4e17784c]
+description = "disallow left empty strand"
+include = false
+
+[db92e77e-7c72-499d-8fe6-9354d2bfd504]
+description = "disallow left empty strand"
+include = false
+reimplements = "5dce058b-28d4-4ca7-aa64-adfe4e17784c"
+
+[b764d47c-83ff-4de2-ab10-6cfe4b15c0f3]
+description = "disallow empty first strand"
+reimplements = "db92e77e-7c72-499d-8fe6-9354d2bfd504"
+
+[38826d4b-16fb-4639-ac3e-ba027dec8b5f]
+description = "disallow right empty strand"
+include = false
+
+[920cd6e3-18f4-4143-b6b8-74270bb8f8a3]
+description = "disallow right empty strand"
+include = false
+reimplements = "38826d4b-16fb-4639-ac3e-ba027dec8b5f"
+
+[9ab9262f-3521-4191-81f5-0ed184a5aa89]
+description = "disallow empty second strand"
+reimplements = "920cd6e3-18f4-4143-b6b8-74270bb8f8a3"

exercises/practice/hamming/Makefile

@@ -0,0 +1,36 @@
+AS = aarch64-linux-gnu-as
+CC = aarch64-linux-gnu-gcc
+
+CFLAGS = -g -Wall -Wextra -pedantic -Werror
+LDFLAGS =
+
+ALL_LDFLAGS = -pie -Wl,--fatal-warnings
+
+ALL_CFLAGS = -std=c99 -fPIE $(CFLAGS)
+ALL_LDFLAGS += $(LDFLAGS)
+
+C_OBJS = $(patsubst %.c,%.o,$(wildcard *.c))
+AS_OBJS = $(patsubst %.s,%.o,$(wildcard *.s))
+ALL_OBJS = $(filter-out example.o,$(C_OBJS) $(AS_OBJS) vendor/unity.o)
+
+CC_CMD = $(CC) $(ALL_CFLAGS) -c -o $@ $<
+
+all: tests
+	qemu-aarch64 -L /usr/aarch64-linux-gnu ./$<
+
+tests: $(ALL_OBJS)
+	@$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) -o $@ $(ALL_OBJS)
+
+%.o: %.s
+	@$(AS) -o $@ $<
+
+%.o: %.c
+	@$(CC_CMD)
+
+vendor/unity.o: vendor/unity.c vendor/unity.h vendor/unity_internals.h
+	@$(CC_CMD)
+
+clean:
+	@rm -f *.o vendor/*.o tests
+
+.PHONY: all clean

exercises/practice/hamming/hamming.s

@@ -0,0 +1,7 @@
+.equ UNEQUAL_LENGTHS, -1
+
+.text
+.globl distance
+
+distance:
+    ret

exercises/practice/hamming/hamming_test.c

@@ -0,0 +1,69 @@
+#include "vendor/unity.h"
+
+#define UNEQUAL_LENGTHS -1
+
+extern int distance(const char *strand1, const char *strand2);
+
+void setUp(void) {
+}
+
+void tearDown(void) {
+}
+
+void test_empty_strands(void) {
+    TEST_ASSERT_EQUAL_INT(0, distance("", ""));
+}
+
+void test_single_letter_identical_strands(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(0, distance("A", "A"));
+}
+
+void test_single_letter_different_strands(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(1, distance("G", "T"));
+}
+
+void test_long_identical_strands(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(0, distance("GGACTGAAATCTG", "GGACTGAAATCTG"));
+}
+
+void test_long_different_strands(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(9, distance("GGACGGATTCTG", "AGGACGGATTCT"));
+}
+
+void test_disallow_first_strand_longer(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(UNEQUAL_LENGTHS, distance("AATG", "AAA"));
+}
+
+void test_disallow_second_strand_longer(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(UNEQUAL_LENGTHS, distance("ATA", "AGTG"));
+}
+
+void test_disallow_empty_first_strand(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(UNEQUAL_LENGTHS, distance("", "G"));
+}
+
+void test_disallow_empty_second_strand(void) {
+    TEST_IGNORE();
+    TEST_ASSERT_EQUAL_INT(UNEQUAL_LENGTHS, distance("G", ""));
+}
+
+int main(void) {
+    UNITY_BEGIN();
+    RUN_TEST(test_empty_strands);
+    RUN_TEST(test_single_letter_identical_strands);
+    RUN_TEST(test_single_letter_different_strands);
+    RUN_TEST(test_long_identical_strands);
+    RUN_TEST(test_long_different_strands);
+    RUN_TEST(test_disallow_first_strand_longer);
+    RUN_TEST(test_disallow_second_strand_longer);
+    RUN_TEST(test_disallow_empty_first_strand);
+    RUN_TEST(test_disallow_empty_second_strand);
+    return UNITY_END();
+}