Add ocr-numbers exercise (#353)

Author: keiravillekode

config.json

@@ -717,6 +717,14 @@
         "prerequisites": [],
         "difficulty": 5
       },
+      {
+        "slug": "ocr-numbers",
+        "name": "OCR Numbers",
+        "uuid": "ab3b1595-ebb0-46ed-ae5c-46e4c254c07e",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 5
+      },
       {
         "slug": "pig-latin",
         "name": "Pig Latin",

exercises/practice/ocr-numbers/.docs/instructions.md

@@ -0,0 +1,47 @@
+# Instructions
+
+Optical Character Recognition or OCR is software that converts images of text into machine-readable text.
+Given a grid of characters representing some digits, convert the grid to a string of digits.
+If the grid has multiple rows of cells, the rows should be separated in the output with a `","`.
+
+- The grid is made of one of more lines of cells.
+- Each line of the grid is made of one or more cells.
+- Each cell is three columns wide and four rows high (3x4) and represents one digit.
+- Digits are drawn using pipes (`"|"`), underscores (`"_"`), and spaces (`" "`).
+
+## Edge cases
+
+- If the input is not a valid size, your program should indicate there is an error.
+- If the input is the correct size, but a cell is not recognizable, your program should output a `"?"` for that character.
+
+## Examples
+
+The following input (without the comments) is converted to `"1234567890"`.
+
+```text
+      _  _     _  _  _  _  _  _  #
+    | _| _||_||_ |_   ||_||_|| | # Decimal numbers.
+    ||_  _|  | _||_|  ||_| _||_| #
+                                 # The fourth line is always blank,
+```
+
+The following input is converted to `"123,456,789"`.
+
+<!-- prettier-ignore-start -->
+
+```text
+    _  _ 
+  | _| _|
+  ||_  _|
+         
+    _  _ 
+|_||_ |_ 
+  | _||_|
+         
+ _  _  _ 
+  ||_||_|
+  ||_| _|
+         
+```
+
+<!-- prettier-ignore-end -->

exercises/practice/ocr-numbers/.docs/introduction.md

@@ -0,0 +1,6 @@
+# Introduction
+
+Your best friend Marta recently landed their dream job working with a local history museum's collections.
+Knowing of your interests in programming, they confide in you about an issue at work for an upcoming exhibit on computing history.
+A local university's math department had donated several boxes of historical printouts, but given the poor condition of the documents, the decision has been made to digitize the text.
+However, the university's old printer had some quirks in how text was represented, and your friend could use your help to extract the data successfully.

exercises/practice/ocr-numbers/.meta/config.json

@@ -0,0 +1,19 @@
+{
+  "authors": [
+    "keiravillekode"
+  ],
+  "files": {
+    "solution": [
+      "source/ocr_numbers.d"
+    ],
+    "test": [
+      "source/ocr_numbers.d"
+    ],
+    "example": [
+      "example/ocr_numbers.d"
+    ]
+  },
+  "blurb": "Given a 3 x 4 grid of pipes, underscores, and spaces, determine which number is represented, or whether it is garbled.",
+  "source": "Inspired by the Bank OCR kata",
+  "source_url": "https://codingdojo.org/kata/BankOCR/"
+}

exercises/practice/ocr-numbers/.meta/tests.toml

@@ -0,0 +1,61 @@
+# 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.
+
+[5ee54e1a-b554-4bf3-a056-9a7976c3f7e8]
+description = "Recognizes 0"
+
+[027ada25-17fd-4d78-aee6-35a19623639d]
+description = "Recognizes 1"
+
+[3cce2dbd-01d9-4f94-8fae-419a822e89bb]
+description = "Unreadable but correctly sized inputs return ?"
+
+[cb19b733-4e36-4cf9-a4a1-6e6aac808b9a]
+description = "Input with a number of lines that is not a multiple of four raises an error"
+
+[235f7bd1-991b-4587-98d4-84206eec4cc6]
+description = "Input with a number of columns that is not a multiple of three raises an error"
+
+[4a841794-73c9-4da9-a779-1f9837faff66]
+description = "Recognizes 110101100"
+
+[70c338f9-85b1-4296-a3a8-122901cdfde8]
+description = "Garbled numbers in a string are replaced with ?"
+
+[ea494ff4-3610-44d7-ab7e-72fdef0e0802]
+description = "Recognizes 2"
+
+[1acd2c00-412b-4268-93c2-bd7ff8e05a2c]
+description = "Recognizes 3"
+
+[eaec6a15-be17-4b6d-b895-596fae5d1329]
+description = "Recognizes 4"
+
+[440f397a-f046-4243-a6ca-81ab5406c56e]
+description = "Recognizes 5"
+
+[f4c9cf6a-f1e2-4878-bfc3-9b85b657caa0]
+description = "Recognizes 6"
+
+[e24ebf80-c611-41bb-a25a-ac2c0f232df5]
+description = "Recognizes 7"
+
+[b79cad4f-e264-4818-9d9e-77766792e233]
+description = "Recognizes 8"
+
+[5efc9cfc-9227-4688-b77d-845049299e66]
+description = "Recognizes 9"
+
+[f60cb04a-42be-494e-a535-3451c8e097a4]
+description = "Recognizes string of decimal numbers"
+
+[b73ecf8b-4423-4b36-860d-3710bdb8a491]
+description = "Numbers separated by empty lines are recognized. Lines are joined by commas."

exercises/practice/ocr-numbers/dub.sdl

@@ -0,0 +1,2 @@
+name "ocr-numbers"
+buildRequirements "disallowDeprecations"

exercises/practice/ocr-numbers/example/ocr_numbers.d

@@ -0,0 +1,52 @@
+module ocr_numbers;
+
+pure string convert(immutable string[] rows)
+{
+    if (rows.length % 4 != 0)
+        throw new Exception("Number of input lines is not a multiple of four");
+
+    if (rows.length > 0 && rows[0].length % 3 != 0)
+        throw new Exception("Number of input columns is not a multiple of three");
+
+    string[] groups;
+    for (size_t g = 0; g < rows.length; g += 4)
+        groups ~= convertGroup(rows[g .. g + 4]);
+
+    import std.array : join;
+    return groups.join(",");
+}
+
+private pure string convertGroup(immutable string[] rows)
+{
+    immutable size_t cols = rows[0].length;
+    char[] result;
+    for (size_t c = 0; c < cols; c += 3)
+        result ~= recognize(rows, c);
+    return cast(string) result;
+}
+
+private pure char recognize(immutable string[] rows, size_t col)
+{
+    immutable string[10][4] patterns = [
+        [" _ ", "   ", " _ ", " _ ", "   ", " _ ", " _ ", " _ ", " _ ", " _ "],
+        ["| |", "  |", " _|", " _|", "|_|", "|_ ", "|_ ", "  |", "|_|", "|_|"],
+        ["|_|", "  |", "|_ ", " _|", "  |", " _|", "|_|", "  |", "|_|", " _|"],
+        ["   ", "   ", "   ", "   ", "   ", "   ", "   ", "   ", "   ", "   "],
+    ];
+
+    foreach (d; 0 .. 10)
+    {
+        bool match = true;
+        foreach (r; 0 .. 4)
+        {
+            if (rows[r][col .. col + 3] != patterns[r][d])
+            {
+                match = false;
+                break;
+            }
+        }
+        if (match)
+            return cast(char)('0' + d);
+    }
+    return '?';
+}