Add micro-blog exercise (#87)

config.json

@@ -122,6 +122,14 @@
         "prerequisites": [],
         "difficulty": 3
       },
+      {
+        "slug": "micro-blog",
+        "name": "Micro Blog",
+        "uuid": "3da09ee9-3f72-4c96-9b07-d1c82566cf65",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 3
+      },
       {
         "slug": "pangram",
         "name": "Pangram",

exercises/practice/micro-blog/.docs/instructions.md

@@ -0,0 +1,37 @@
+# Instructions
+
+You have identified a gap in the social media market for very very short posts.
+Now that Twitter allows 280 character posts, people wanting quick social media updates aren't being served.
+You decide to create your own social media network.
+
+To make your product noteworthy, you make it extreme and only allow posts of 5 or less characters.
+Any posts of more than 5 characters should be truncated to 5.
+
+To allow your users to express themselves fully, you allow Emoji and other Unicode.
+
+The task is to truncate input strings to 5 characters.
+
+## Text Encodings
+
+Text stored digitally has to be converted to a series of bytes.
+There are 3 ways to map characters to bytes in common use.
+
+- **ASCII** can encode English language characters.
+  All characters are precisely 1 byte long.
+- **UTF-8** is a Unicode text encoding.
+  Characters take between 1 and 4 bytes.
+- **UTF-16** is a Unicode text encoding.
+  Characters are either 2 or 4 bytes long.
+
+UTF-8 and UTF-16 are both Unicode encodings which means they're capable of representing a massive range of characters including:
+
+- Text in most of the world's languages and scripts
+- Historic text
+- Emoji
+
+UTF-8 and UTF-16 are both variable length encodings, which means that different characters take up different amounts of space.
+
+Consider the letter 'a' and the emoji '😛'.
+In UTF-16 the letter takes 2 bytes but the emoji takes 4 bytes.
+
+The trick to this exercise is to use APIs designed around Unicode characters (codepoints) instead of Unicode codeunits.

exercises/practice/micro-blog/.meta/config.json

@@ -0,0 +1,17 @@
+{
+  "authors": [
+    "keiravillekode"
+  ],
+  "files": {
+    "solution": [
+      "micro_blog.s"
+    ],
+    "test": [
+      "micro_blog_test.c"
+    ],
+    "example": [
+      ".meta/example.s"
+    ]
+  },
+  "blurb": "Given an input string, truncate it to 5 characters."
+}

exercises/practice/micro-blog/.meta/example.s

@@ -0,0 +1,23 @@
+.text
+.globl truncate
+
+/* extern void truncate(char *buffer, const char *phrase); */
+truncate:
+        mov     x2, #6
+
+.read:
+        ldrb    w3, [x1], #1            /* load byte, post-increment */
+        strb    w3, [x0], #1            /* store byte, post-increment */
+        cbz     w3, .return             /* null terminator */
+
+        and     w4, w3, #0xC0
+        cmp     w4, #0x80
+        beq     .read                   /* non-initial byte of code point */
+
+        sub     x2, x2, #1
+        cbnz    x2, .read
+                                        /* start of the 6th code point */
+
+.return:
+        strb    wzr, [x0, #-1]          /* overwrite most recent byte with '\0' */
+        ret

exercises/practice/micro-blog/.meta/tests.toml

@@ -0,0 +1,46 @@
+# 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.
+
+[b927b57f-7c98-42fd-8f33-fae091dc1efc]
+description = "English language short"
+
+[a3fcdc5b-0ed4-4f49-80f5-b1a293eac2a0]
+description = "English language long"
+
+[01910864-8e15-4007-9c7c-ac956c686e60]
+description = "German language short (broth)"
+
+[f263e488-aefb-478f-a671-b6ba99722543]
+description = "German language long (bear carpet → beards)"
+
+[0916e8f1-41d7-4402-a110-b08aa000342c]
+description = "Bulgarian language short (good)"
+
+[bed6b89c-03df-4154-98e6-a61a74f61b7d]
+description = "Greek language short (health)"
+
+[485a6a70-2edb-424d-b999-5529dbc8e002]
+description = "Maths short"
+
+[8b4b7b51-8f48-4fbe-964e-6e4e6438be28]
+description = "Maths long"
+
+[71f4a192-0566-4402-a512-fe12878be523]
+description = "English and emoji short"
+
+[6f0f71f3-9806-4759-a844-fa182f7bc203]
+description = "Emoji short"
+
+[ce71fb92-5214-46d0-a7f8-d5ba56b4cc6e]
+description = "Emoji long"
+
+[5dee98d2-d56e-468a-a1f2-121c3f7c5a0b]
+description = "Royal Flush?"

exercises/practice/micro-blog/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/micro-blog/micro_blog.s

@@ -0,0 +1,5 @@
+.text
+.globl truncate
+
+truncate:
+    ret

exercises/practice/micro-blog/micro_blog_test.c

@@ -0,0 +1,123 @@
+#include "vendor/unity.h"
+
+#define BUFFER_SIZE 40
+
+extern void truncate(char *buffer, const char *phrase);
+
+void setUp(void) {
+}
+
+void tearDown(void) {
+}
+
+void test_english_language_short(void) {
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "Hi");
+    TEST_ASSERT_EQUAL_STRING("Hi", buffer);
+}
+
+void test_english_language_long(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "Hello there");
+    TEST_ASSERT_EQUAL_STRING("Hello", buffer);
+}
+
+void test_german_language_short_broth(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "brühe");
+    TEST_ASSERT_EQUAL_STRING("brühe", buffer);
+}
+
+void test_german_language_long_bear_carpet__beards(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "Bärteppich");
+    TEST_ASSERT_EQUAL_STRING("Bärte", buffer);
+}
+
+void test_bulgarian_language_short_good(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "Добър");
+    TEST_ASSERT_EQUAL_STRING("Добър", buffer);
+}
+
+void test_greek_language_short_health(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "υγειά");
+    TEST_ASSERT_EQUAL_STRING("υγειά", buffer);
+}
+
+void test_maths_short(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "a=πr²");
+    TEST_ASSERT_EQUAL_STRING("a=πr²", buffer);
+}
+
+void test_maths_long(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "∅⊊ℕ⊊ℤ⊊ℚ⊊ℝ⊊ℂ");
+    TEST_ASSERT_EQUAL_STRING("∅⊊ℕ⊊ℤ", buffer);
+}
+
+void test_english_and_emoji_short(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "Fly 🛫");
+    TEST_ASSERT_EQUAL_STRING("Fly 🛫", buffer);
+}
+
+void test_emoji_short(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "💇");
+    TEST_ASSERT_EQUAL_STRING("💇", buffer);
+}
+
+void test_emoji_long(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "❄🌡🤧🤒🏥🕰😀");
+    TEST_ASSERT_EQUAL_STRING("❄🌡🤧🤒🏥", buffer);
+}
+
+void test_royal_flush(void) {
+    TEST_IGNORE();
+    char buffer[BUFFER_SIZE];
+
+    truncate(buffer, "🃎🂸🃅🃋🃍🃁🃊");
+    TEST_ASSERT_EQUAL_STRING("🃎🂸🃅🃋🃍", buffer);
+}
+
+int main(void) {
+    UNITY_BEGIN();
+    RUN_TEST(test_english_language_short);
+    RUN_TEST(test_english_language_long);
+    RUN_TEST(test_german_language_short_broth);
+    RUN_TEST(test_german_language_long_bear_carpet__beards);
+    RUN_TEST(test_bulgarian_language_short_good);
+    RUN_TEST(test_greek_language_short_health);
+    RUN_TEST(test_maths_short);
+    RUN_TEST(test_maths_long);
+    RUN_TEST(test_english_and_emoji_short);
+    RUN_TEST(test_emoji_short);
+    RUN_TEST(test_emoji_long);
+    RUN_TEST(test_royal_flush);
+    return UNITY_END();
+}