Skip to content

Commit

Permalink
Merge pull request #138 from Peefy/feat-difflib-module
Browse files Browse the repository at this point in the history
feat: add difflib module to help kcl unit test cases
  • Loading branch information
Peefy authored May 23, 2024
2 parents ebb8ed7 + 08d77ef commit de2f798
Show file tree
Hide file tree
Showing 5 changed files with 220 additions and 0 deletions.
62 changes: 62 additions & 0 deletions difflib/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
## Introduction

Module `difflib` -- helpers for computing deltas between objects.

## How to Use

+ Add the dependency

```shell
kcl mod add difflib
```

+ Write the code

```python
import difflib
import yaml

data1 = {
"firstName": "John",
"lastName": "Doe",
"age": 30,
"address": {
"streetAddress": "1234 Main St",
"city": "New York",
"state": "NY",
"postalCode": "10001"
},
"phoneNumbers": [
{
"type": "home",
"number": "212-555-1234"
},
{
"type": "work",
"number": "646-555-5678"
}
]
}
data2 = {
"firstName": "John",
"lastName": "Doe",
"age": 30,
"address": {
"streetAddress": "1234 Main St",
"city": "New York",
"state": "NY",
"postalCode": None
},
"phoneNumbers": [
{
"type": "work",
"number": "646-555-5678"
}
]
}
diff = difflib.diff(yaml.encode(data1), yaml.encode(data2))
```

## Resource

The code source and documents are [here](https://github.com/kcl-lang/artifacthub/tree/main/difflib)
5 changes: 5 additions & 0 deletions difflib/kcl.mod
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
[package]
name = "difflib"
edition = "v0.9.0"
version = "0.1.0"

Empty file added difflib/kcl.mod.lock
Empty file.
108 changes: 108 additions & 0 deletions difflib/main.k
Original file line number Diff line number Diff line change
@@ -0,0 +1,108 @@
"""Module difflib -- helpers for computing deltas between objects.
"""

_looper_n = lambda elements: [any], n: int, func: (any, any) -> any, initial: any -> any {
assert n >= 0
result = initial
if n < len(elements):
result = _looper_n(elements, n + 1, func, func(result, elements[n]))

result
}

looper = lambda initial: any, elements: [any], func: (any, any) -> any -> any {
_looper_n(elements, 0, func, initial)
}

looper_enumerate = lambda initial: any, elements: [any] | {str:}, func: (any, str | int, any) -> any -> any {
looper(initial, [{"k" = k, "v" = v} for k, v in elements], lambda initial, value {
func(initial, value.k, value.v)
})
}

for_each = lambda elements: [any], func: (any) {
[func(i) for i in elements]
Undefined
}

while_loop = lambda condition: ([any]) -> bool, body: ([any]) -> [any], vals: [any] -> [any] {
"""Do a while loop using the condition function, body function and variables with side effects that need to be modified in place, such as iteration variables, etc."""
vals if not condition(vals) else while_loop(condition, body, body(vals))
}

list_set_index = lambda l: [], i: int, v {
"""Set the list `l` at index `i` with the value `v`"""
l = l[:i:] + [v] + l[i + 1::]
l
}

longest_common_subsequence = lambda a: [], b: [] -> [] {
"""Longest Common Subsequence (LCS) is a typical algorithm for calculating the length of the longest common subsequence between two sequences."""
# Build the lengths matrix for dp
lengths = [[0] * (len(b) + 1) for _ in range(len(a) + 1)]
lengths = looper_enumerate(lengths, a, lambda m, i, x {
looper_enumerate(m, b, lambda v, j, y {
list_set_index(v, i + 1, list_set_index(v[i + 1], j + 1, v[i][j] + 1 if x == y else max(v[i + 1][j], v[i][j + 1])))
})
})
vals = [len(a), len(b), []]
# Read the substrings out from the matrix
while_loop(lambda vals: [any] {
vals[0] != 0 and vals[1] != 0
}, lambda vals: [any] {
x = vals[0]
y = vals[1]
result = vals[2]
if lengths[x][y] == lengths[x - 1][y]:
x -= 1
elif lengths[x][y] == lengths[x][y - 1]:
y -= 1
else:
assert a[x - 1] == b[y - 1], "{} != {}".format(a[x - 1], b[y - 1])
result = [a[x - 1]] + result
x -= 1
y -= 1
[x, y, result]
}, vals)[-1]
}

ndiff = lambda a: [str], b: [str] -> str {
"""Compare a and b (lists of strings); return a Differ-style delta string."""
lcs = longest_common_subsequence(a, b)
# while loop variabels: [i, j, lcs, diff_str]
vals = [0, 0, lcs, ""]
len_a = len(a)
len_b = len(b)
while_loop(lambda vals {
vals[0] < len_a or vals[1] < len_b
}, lambda vals {
i = vals[0]
j = vals[1]
lcs = vals[2]
diff_str = vals[3]
if i < len(a) and j < len(b) and a[i] == b[j]:
diff_str += " " + a[i] + "\n"
i += 1
j += 1
elif j < len(b) and (not lcs or i >= len(a) or a[i] != lcs[0]):
diff_str += "+ " + b[j] + "\n"
j += 1
elif i < len(a) and (not lcs or j >= len(b) or b[j] != lcs[0]):
diff_str += "- " + a[i] + "\n"
i += 1
else:
if lcs:
lcs = lcs[1:]
if i < len(a):
i += 1
if j < len(b):
j += 1

[i, j, lcs, diff_str]
}, vals)[-1]
}

diff = lambda a: str, b: str {
"""Compare a and b (string type); return a Differ-style delta string."""
ndiff(a.splitlines(), b.splitlines())
}
45 changes: 45 additions & 0 deletions difflib/main_test.k
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
import yaml

schema Suite:
a: str
b: str
result: str

test_longest_common_subsequence = lambda {
cases: [Suite] = [
Suite {
a: "\n".join(["this", "is", "a", "example", "xxx"])
b: "\n".join(["this", "is", "an", "example", "xxx"])
result: """ this
is
+ an
+ example
+ xxx
- a
- example
- xxx
"""
}
Suite {
a: yaml.encode({
"a": 1
"b": 2
})
b: yaml.encode({
"a": 1
"c": 1
"d": 3
"b": 2
})
result: """ a: 1
+ c: 1
+ d: 3
b: 2
"""
}
]
for_each(cases, lambda case: Suite {
result = diff(case.a, case.b)
assert result == case.result, "expect ${case.result}, got ${result}"
})
}

0 comments on commit de2f798

Please sign in to comment.