implement variable-length-quantity exercise

Author: Wiguwbe

config.json

@@ -635,6 +635,14 @@
           "structs"
         ]
       },
+      {
+        "slug": "variable-length-quantity",
+        "name": "Variable Length Quantity",
+        "uuid": "318e1e7c-fc3a-4ec6-a47d-f8526d032b4f",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 4
+      },
       {
         "slug": "spiral-matrix",
         "name": "Spiral Matrix",
@@ -1263,3 +1271,4 @@
     "used_for/scientific_calculations"
   ]
 }
+

exercises/practice/variable-length-quantity/.docs/instructions.md

@@ -0,0 +1,34 @@
+# Instructions
+
+Implement variable length quantity encoding and decoding.
+
+The goal of this exercise is to implement [VLQ][vlq] encoding/decoding.
+
+In short, the goal of this encoding is to encode integer values in a way that would save bytes.
+Only the first 7 bits of each byte are significant (right-justified; sort of like an ASCII byte).
+So, if you have a 32-bit value, you have to unpack it into a series of 7-bit bytes.
+Of course, you will have a variable number of bytes depending upon your integer.
+To indicate which is the last byte of the series, you leave bit #7 clear.
+In all of the preceding bytes, you set bit #7.
+
+So, if an integer is between `0-127`, it can be represented as one byte.
+Although VLQ can deal with numbers of arbitrary sizes, for this exercise we will restrict ourselves to only numbers that fit in a 32-bit unsigned integer.
+Here are examples of integers as 32-bit values, and the variable length quantities that they translate to:
+
+```text
+ NUMBER        VARIABLE QUANTITY
+00000000              00
+00000040              40
+0000007F              7F
+00000080             81 00
+00002000             C0 00
+00003FFF             FF 7F
+00004000           81 80 00
+00100000           C0 80 00
+001FFFFF           FF FF 7F
+00200000          81 80 80 00
+08000000          C0 80 80 00
+0FFFFFFF          FF FF FF 7F
+```
+
+[vlq]: https://en.wikipedia.org/wiki/Variable-length_quantity

exercises/practice/variable-length-quantity/.meta/config.json

@@ -0,0 +1,21 @@
+{
+  "authors": [
+    "Wiguwbe"
+  ],
+  "files": {
+    "solution": [
+      "variable_length_quantity.c",
+      "variable_length_quantity.h"
+    ],
+    "test": [
+      "test_variable_length_quantity.c"
+    ],
+    "example": [
+      ".meta/example.c",
+      ".meta/example.h"
+    ]
+  },
+  "blurb": "Implement variable length quantity encoding and decoding.",
+  "source": "A poor Splice developer having to implement MIDI encoding/decoding.",
+  "source_url": "https://splice.com"
+}

exercises/practice/variable-length-quantity/.meta/example.c

@@ -0,0 +1,70 @@
+#include "variable_length_quantity.h"
+
+#include <string.h>
+
+#define I_BUF_SIZE 5
+
+#define SQLite_VARINT 0
+
+int encode(uint64_t *integers, int integers_len, uint8_t *output)
+{
+   int output_index = 0;
+   uint8_t buf[I_BUF_SIZE];
+   for (int i = 0; i < integers_len; i++) {
+      uint64_t integer = integers[i];
+      uint8_t mask = 0;
+      int buf_idx = I_BUF_SIZE;
+      do {
+         uint8_t part = (uint8_t)(integer & 0x7f);
+         integer >>= 7;
+         buf[--buf_idx] = part | mask;
+         mask |= 0x80;
+      } while (integer);
+      int buf_len = I_BUF_SIZE - buf_idx;
+      memcpy(output + output_index, buf + buf_idx, buf_len);
+      output_index += buf_len;
+   }
+   return output_index;
+}
+
+int decode(uint8_t *buffer, int buffer_len, uint64_t *output)
+{
+   int output_index = 0;
+   int buffer_index = 0;
+   uint64_t cur = 0;
+   int cur_count = 0;
+   while (buffer_index < buffer_len) {
+      uint8_t byte = buffer[buffer_index++];
+      cur_count++;
+#if SQLite_VARINT == 1
+      /*
+         The exercise and test data, as they stand, only handle 32-bit
+         integers.
+         This is a specific use case to decode SQLite Varints, which are
+         64-bit and truncated to 9 bytes when encoded.
+         When decoding, the 9th byte, if there is one, uses the full 8 bits for
+         the value.
+         Finding the 9th byte also marks the end of an integer.
+      */
+      if (cur_count == 9) {
+         cur <<= 8;
+         cur |= byte;
+         output[output_index++] = cur;
+         cur = 0;
+         cur_count = 0;
+         continue;
+      }
+#endif
+      cur <<= 7;
+      cur |= byte & 0x7f;
+      if (!(byte & 0x80)) {
+         output[output_index++] = cur;
+         cur = 0;
+         cur_count = 0;
+         continue;
+      }
+   }
+   if (cur_count || cur)
+      return -1;
+   return output_index;
+}

exercises/practice/variable-length-quantity/.meta/example.h

@@ -0,0 +1,12 @@
+#ifndef VLQ_H
+#define VLQ_H
+
+#include <stdint.h>
+
+// return output_len
+int encode(uint64_t *integers, int integers_len, uint8_t *output);
+
+// return output_len, -1 on error
+int decode(uint8_t *buffer, int buffer_len, uint64_t *output);
+
+#endif

exercises/practice/variable-length-quantity/.meta/tests.toml

@@ -0,0 +1,88 @@
+# 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.
+
+[35c9db2e-f781-4c52-b73b-8e76427defd0]
+description = "Encode a series of integers, producing a series of bytes. -> zero"
+
+[be44d299-a151-4604-a10e-d4b867f41540]
+description = "Encode a series of integers, producing a series of bytes. -> arbitrary single byte"
+
+[ea399615-d274-4af6-bbef-a1c23c9e1346]
+description = "Encode a series of integers, producing a series of bytes. -> largest single byte"
+
+[77b07086-bd3f-4882-8476-8dcafee79b1c]
+description = "Encode a series of integers, producing a series of bytes. -> smallest double byte"
+
+[63955a49-2690-4e22-a556-0040648d6b2d]
+description = "Encode a series of integers, producing a series of bytes. -> arbitrary double byte"
+
+[29da7031-0067-43d3-83a7-4f14b29ed97a]
+description = "Encode a series of integers, producing a series of bytes. -> largest double byte"
+
+[3345d2e3-79a9-4999-869e-d4856e3a8e01]
+description = "Encode a series of integers, producing a series of bytes. -> smallest triple byte"
+
+[5df0bc2d-2a57-4300-a653-a75ee4bd0bee]
+description = "Encode a series of integers, producing a series of bytes. -> arbitrary triple byte"
+
+[f51d8539-312d-4db1-945c-250222c6aa22]
+description = "Encode a series of integers, producing a series of bytes. -> largest triple byte"
+
+[da78228b-544f-47b7-8bfe-d16b35bbe570]
+description = "Encode a series of integers, producing a series of bytes. -> smallest quadruple byte"
+
+[11ed3469-a933-46f1-996f-2231e05d7bb6]
+description = "Encode a series of integers, producing a series of bytes. -> arbitrary quadruple byte"
+
+[d5f3f3c3-e0f1-4e7f-aad0-18a44f223d1c]
+description = "Encode a series of integers, producing a series of bytes. -> largest quadruple byte"
+
+[91a18b33-24e7-4bfb-bbca-eca78ff4fc47]
+description = "Encode a series of integers, producing a series of bytes. -> smallest quintuple byte"
+
+[5f34ff12-2952-4669-95fe-2d11b693d331]
+description = "Encode a series of integers, producing a series of bytes. -> arbitrary quintuple byte"
+
+[7489694b-88c3-4078-9864-6fe802411009]
+description = "Encode a series of integers, producing a series of bytes. -> maximum 32-bit integer input"
+
+[f9b91821-cada-4a73-9421-3c81d6ff3661]
+description = "Encode a series of integers, producing a series of bytes. -> two single-byte values"
+
+[68694449-25d2-4974-ba75-fa7bb36db212]
+description = "Encode a series of integers, producing a series of bytes. -> two multi-byte values"
+
+[51a06b5c-de1b-4487-9a50-9db1b8930d85]
+description = "Encode a series of integers, producing a series of bytes. -> many multi-byte values"
+
+[baa73993-4514-4915-bac0-f7f585e0e59a]
+description = "Decode a series of bytes, producing a series of integers. -> one byte"
+
+[72e94369-29f9-46f2-8c95-6c5b7a595aee]
+description = "Decode a series of bytes, producing a series of integers. -> two bytes"
+
+[df5a44c4-56f7-464e-a997-1db5f63ce691]
+description = "Decode a series of bytes, producing a series of integers. -> three bytes"
+
+[1bb58684-f2dc-450a-8406-1f3452aa1947]
+description = "Decode a series of bytes, producing a series of integers. -> four bytes"
+
+[cecd5233-49f1-4dd1-a41a-9840a40f09cd]
+description = "Decode a series of bytes, producing a series of integers. -> maximum 32-bit integer"
+
+[e7d74ba3-8b8e-4bcb-858d-d08302e15695]
+description = "Decode a series of bytes, producing a series of integers. -> incomplete sequence causes error"
+
+[aa378291-9043-4724-bc53-aca1b4a3fcb6]
+description = "Decode a series of bytes, producing a series of integers. -> incomplete sequence causes error, even if value is zero"
+
+[a91e6f5a-c64a-48e3-8a75-ce1a81e0ebee]
+description = "Decode a series of bytes, producing a series of integers. -> multiple values"

exercises/practice/variable-length-quantity/makefile

@@ -0,0 +1,37 @@
+### If you wish to use extra libraries (math.h for instance),
+### add their flags here (-lm in our case) in the "LIBS" variable.
+
+LIBS = -lm
+
+###
+CFLAGS  = -std=c99
+CFLAGS += -g
+CFLAGS += -Wall
+CFLAGS += -Wextra
+CFLAGS += -pedantic
+CFLAGS += -Werror
+CFLAGS += -Wmissing-declarations
+CFLAGS += -DUNITY_SUPPORT_64 -DUNITY_OUTPUT_COLOR
+
+ASANFLAGS  = -fsanitize=address
+ASANFLAGS += -fno-common
+ASANFLAGS += -fno-omit-frame-pointer
+
+.PHONY: test
+test: tests.out
+	@./tests.out
+
+.PHONY: memcheck
+memcheck: ./*.c ./*.h
+	@echo Compiling $@
+	@$(CC) $(ASANFLAGS) $(CFLAGS) test-framework/unity.c ./*.c -o memcheck.out $(LIBS)
+	@./memcheck.out
+	@echo "Memory check passed"
+
+.PHONY: clean
+clean:
+	rm -rf *.o *.out *.out.dSYM
+
+tests.out: ./*.c ./*.h
+	@echo Compiling $@
+	@$(CC) $(CFLAGS) test-framework/unity.c ./*.c -o tests.out $(LIBS)