mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2023-12-21 10:23:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

Elaborate on transforms and implement changes

Browse Source
This commit is contained in:
Joscha 2021-04-29 20:13:46 +02:00
parent 9ec19be113
commit e7a51decb0
2 changed files with 120 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
CONFIG.md
View File

@ -107,6 +107,21 @@ The `-re->` arrow uses regular expressions. `SOURCE` is a regular expression
that must match the entire path. If this is the case, then the capturing groups
are available in `TARGET` for formatting.
`TARGET` uses Python's [format string syntax][3]. The *n*-th capturing group can
be referred to as `{g<n>}` (e. g. `{g3}`). `{g0}` refers to the original path.
If capturing group *n*'s contents are a valid integer, the integer value is
available as `{i<n>}` (e. g. `{i3}`). If capturing group *n*'s contents are a
valid float, the float value is available as `{f<n>}` (e. g. `{f3}`).
Python's format string syntax has rich options for formatting its arguments. For
example, to left-pad the capturing group 3 with the digit `0` to width 5, you
can use `{i3:05}`.
PFERD even allows you to write entire expressions inside the curly braces, for
example `{g2.lower()}` or `{g3.replace(' ', '_')}`.
[3]: <https://docs.python.org/3/library/string.html#format-string-syntax> "Format String Syntax"
### Example: Tutorials
You have ILIAS course with lots of tutorials, but are only interested in a
@ -136,3 +151,24 @@ the `tutorials/` directory and thus not discover that `tutorials/tut02/`
existed.
Since the second rule is only relevant for crawling, the `TARGET` is left out.
### Example: Lecture slides
You have a course with slides like `Lecture 3: Linear functions.PDF` and you
would like to rename them to `03_linear_functions.pdf`.
```
Lectures/
|- Lecture 1: Introduction.PDF
|- Lecture 2: Vectors and matrices.PDF
|- Lecture 3: Linear functions.PDF
...
```
To do this, you can use the most powerful of arrows, the regex arrow.
```
"Lectures/Lecture (\\d+): (.*)\\.PDF" -re-> "Lectures/{i1:02}_{g2.lower().replace(' ', '_')}.pdf"
```
Note the escaped backslashes on the `SOURCE` side.

103
PFERD/transformer.py
View File

@ -1,3 +1,9 @@
# I'm sorry that this code has become a bit dense and unreadable. While
# reading, it is important to remember what True and False mean. I'd love to
# have some proper sum-types for the inputs and outputs, they'd make this code
# a lot easier to understand.
import ast
import re
from abc import ABC, abstractmethod
from dataclasses import dataclass
@ -7,12 +13,23 @@ from typing import Dict, Optional, Union
class Rule(ABC):
@abstractmethod
def transform(self, path: PurePath) -> Optional[PurePath]:
def transform(self, path: PurePath) -> Union[PurePath, bool]:
"""
Try to apply this rule to the path. Returns another path if the rule
was successfully applied, True if the rule matched but resulted in an
exclamation mark, and False if the rule didn't match at all.
"""
pass
# These rules all use a Union[T, bool] for their right side. They are passed a
# T if the arrow's right side was a normal string, True if it was an
# exclamation mark and False if it was missing entirely.
class NormalRule(Rule):
def __init__(self, left: PurePath, right: PurePath):
def __init__(self, left: PurePath, right: Union[PurePath, bool]):
self._left = left
self._right = right
@ -35,49 +52,61 @@ class NormalRule(Rule):
return PurePath(*path_parts)
def transform(self, path: PurePath) -> Optional[PurePath]:
def transform(self, path: PurePath) -> Union[PurePath, bool]:
if rest := self._match_prefix(path):
if isinstance(self._right, bool):
return self._right or path
else:
return self._right / rest
return None
return False
class ExactRule(Rule):
def __init__(self, left: PurePath, right: PurePath):
def __init__(self, left: PurePath, right: Union[PurePath, bool]):
self._left = left
self._right = right
def transform(self, path: PurePath) -> Optional[PurePath]:
def transform(self, path: PurePath) -> Union[PurePath, bool]:
if path == self._left:
if isinstance(self._right, bool):
return self._right or path
else:
return self._right
return None
return False
class ReRule(Rule):
def __init__(self, left: str, right: str):
def __init__(self, left: str, right: Union[str, bool]):
self._left = left
self._right = right
def transform(self, path: PurePath) -> Optional[PurePath]:
def transform(self, path: PurePath) -> Union[PurePath, bool]:
if match := re.fullmatch(self._left, str(path)):
kwargs: Dict[str, Union[int, float]] = {}
if isinstance(self._right, bool):
return self._right or path
vars: Dict[str, Union[str, int, float]] = {}
groups = [match[0]] + list(match.groups())
for i, group in enumerate(groups):
vars[f"g{i}"] = group
try:
kwargs[f"i{i}"] = int(group)
vars[f"i{i}"] = int(group)
except ValueError:
pass
try:
kwargs[f"f{i}"] = float(group)
vars[f"f{i}"] = float(group)
except ValueError:
pass
return PurePath(self._right.format(*groups, **kwargs))
result = eval(f"f{self._right!r}", vars)
return PurePath(result)
return None
return False
@dataclass
@ -136,7 +165,9 @@ QUOTATION_MARKS = {'"', "'"}
def parse_string_literal(line: Line) -> str:
escaped = False
result = []
# Points to first character of string literal
start_index = line.index
quotation_mark = line.get()
if quotation_mark not in QUOTATION_MARKS:
@ -147,17 +178,17 @@ def parse_string_literal(line: Line) -> str:
while c := line.get():
if escaped:
result.append(c)
escaped = False
line.advance()
elif c == quotation_mark:
line.advance()
return "".join(result)
stop_index = line.index
literal = line.line[start_index:stop_index]
return ast.literal_eval(literal)
elif c == "\\":
escaped = True
line.advance()
else:
result.append(c)
line.advance()
raise RuleParseException(line, "Expected end of string literal")
@ -174,11 +205,14 @@ def parse_until_space_or_eol(line: Line) -> str:
return "".join(result)
def parse_string(line: Line) -> str:
def parse_string(line: Line) -> Union[str, bool]:
if line.get() in QUOTATION_MARKS:
return parse_string_literal(line)
else:
return parse_until_space_or_eol(line)
string = parse_until_space_or_eol(line)
if string == "!":
return True
return string
def parse_arrow(line: Line) -> str:
@ -200,17 +234,35 @@ def parse_arrow(line: Line) -> str:
def parse_rule(line: Line) -> Rule:
# Parse left side
leftindex = line.index
left = parse_string(line)
if isinstance(left, bool):
line.index = leftindex
raise RuleParseException(line, "Left side can't be '!'")
# Parse arrow
line.expect(" ")
arrowindex = line.index
arrowname = parse_arrow(line)
# Parse right side
if line.get():
line.expect(" ")
right = parse_string(line)
else:
right = False
rightpath: Union[PurePath, bool]
if isinstance(right, bool):
rightpath = right
else:
rightpath = PurePath(right)
# Dispatch
if arrowname == "":
return NormalRule(PurePath(left), PurePath(right))
return NormalRule(PurePath(left), rightpath)
elif arrowname == "exact":
return ExactRule(PurePath(left), PurePath(right))
return ExactRule(PurePath(left), rightpath)
elif arrowname == "re":
return ReRule(left, right)
else:
@ -232,7 +284,12 @@ class Transformer:
def transform(self, path: PurePath) -> Optional[PurePath]:
for rule in self._rules:
if result := rule.transform(path):
result = rule.transform(path)
if isinstance(result, PurePath):
return result
elif result: # Exclamation mark
return None
else:
continue
return None