Skip to content

add batch of string ops #20826

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
eellison wants to merge 4 commits into from
Closed

add batch of string ops #20826

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
041c128
add string ops
May 22, 2019
a4152f5
add test case
May 22, 2019
2d984f2
try to fix windows build by including ctype
May 23, 2019
57e42f4
Merge branch 'master' of https://github.com/pytorch/pytorch into stri…
May 23, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 20 additions & 5 deletions test/test_jit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12079,14 +12079,29 @@ def fn(x):

self.checkScript(fn, ("abcde",))

def test_str_cmp(self):
def test(a, b):
def test_str_ops(self):
def test_str_is(s):
# type: (str) -> Tuple[bool, bool, bool, bool, bool, bool]
return s.isupper(), s.islower(), s.isdigit(), s.isspace(), \
s.isalnum(), s.isalpha()

def test_str_to(s):
# type: (str) -> Tuple[str, str]
return s.upper(), s.lower()

inputs = ["", "12a", "!B", "12", "a", "B", "aB", "$12", "B12", "AB ",
Copy link
Contributor

@driazati driazati May 22, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

needs a >1 char string of lowers: "aaaa" or something

" \t", " \n", "\na", "abc"]

for input in inputs:
self.checkScript(test_str_is, (input,))
self.checkScript(test_str_to, (input,))

def test_str_cmp(a, b):
# type: (str, str) -> Tuple[bool, bool, bool, bool, bool, bool]
return a != b, a == b, a < b, a > b, a <= b, a >= b

self.checkScript(test, ("1", "2"))
self.checkScript(test, ("2", "1"))
self.checkScript(test, ("1", "1"))
for i in range(len(inputs) - 1):
self.checkScript(test_str_cmp, (inputs[i], inputs[i + 1]))

def test_ord(self):
def fn(x):
Expand Down
65 changes: 65 additions & 0 deletions torch/csrc/jit/register_prim_ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
#include <c10/core/thread_pool.h>
#include <c10/util/SmallVector.h>

#include <cctype>
#include <algorithm>
#include <cmath>
#include <exception>
Expand Down Expand Up @@ -1913,6 +1914,70 @@ RegisterOperators reg2({
Operator(
"aten::slice(str string, int start, int end=9223372036854775807, int step=1) -> str",
stringSlice),

// python string is methods return false if empty
#define DEFINE_STRING_IS_OP(op_name, char_op) \
Operator(#op_name "(str self) -> bool", [](Stack& stack) { \
auto string = pop(stack).toStringRef(); \
push( \
stack, \
string.size() != 0 && \
std::all_of(string.begin(), string.end(), [](char c) { \
return char_op(c); \
})); \
return 0; \
})

// upper and lower require there to be at least one alpha character,
// and ignore all other characters
Operator(
"aten::isupper(str self) -> bool",
[](Stack& stack) {
auto string = pop(stack).toStringRef();
bool found_alpha = false;
bool is_upper = true;
for (size_t i = 0; i < string.size() && is_upper; ++i) {
char c = string[i];
found_alpha |= std::isalpha(c);
is_upper &= (!std::isalpha(c) || std::isupper(c));
}
push(stack, found_alpha && is_upper);
return 0;
}),
Operator(
"aten::islower(str self) -> bool",
[](Stack& stack) {
auto string = pop(stack).toStringRef();
bool found_alpha = false;
bool is_lower = true;
for (size_t i = 0; i < string.size() && is_lower; ++i) {
char c = string[i];
found_alpha |= std::isalpha(c);
is_lower &= (!std::isalpha(c) || std::islower(c));
}
push(stack, found_alpha && is_lower);
return 0;
}),

DEFINE_STRING_IS_OP(aten::isdigit, std::isdigit),
DEFINE_STRING_IS_OP(aten::isspace, std::isspace),
DEFINE_STRING_IS_OP(aten::isalnum, std::isalnum),
DEFINE_STRING_IS_OP(aten::isalpha, std::isalpha),

#define DEFINE_STRING_CHAR_MAP_OP(op_name, char_op) \
Operator(#op_name "(str self) -> str", [](Stack& stack) { \
auto string = pop(stack).toStringRef(); \
std::stringstream ss; \
for (char c : string) { \
ss << static_cast<char>(char_op(c)); \
} \
push(stack, ss.str()); \
return 0; \
})

DEFINE_STRING_CHAR_MAP_OP(aten::upper, std::toupper),
DEFINE_STRING_CHAR_MAP_OP(aten::lower, std::tolower),

Operator(
"prim::StringIndex(str string, int index) -> str",
[](Stack& stack) {
Expand Down