|
|
| LOGGER = logging.getLogger(__name__) |
| |
|
| RARE_RE = re.compile(r"\+-|\.\.|\?\?\?\?|!!!!|,,|--") |
| |
|
| SCOPED_ABBR_RE = re.compile(r"\((c|tm|r)\)", flags=re.IGNORECASE) |
| |
|
| PLUS_MINUS_RE = re.compile(r"\+-") |
| |
|
| ELLIPSIS_RE = re.compile(r"\.{2,}") |
| |
|
| ELLIPSIS_QUESTION_EXCLAMATION_RE = re.compile(r"([?!])…") |
| |
|
| QUESTION_EXCLAMATION_RE = re.compile(r"([?!]){4,}") |
| |
|
| COMMA_RE = re.compile(r",{2,}") |
| |
|
| EM_DASH_RE = re.compile(r"(^|[^-])---(?=[^-]|$)", flags=re.MULTILINE) |
| |
|
| EN_DASH_RE = re.compile(r"(^|\s)--(?=\s|$)", flags=re.MULTILINE) |
| |
|
| EN_DASH_INDENT_RE = re.compile(r"(^|[^-\s])--(?=[^-\s]|$)", flags=re.MULTILINE) |
| |
|
dict | SCOPED_ABBR = {"c": "©", "r": "®", "tm": "™"} |
| |
Simple typographic replacements
* ``(c)``, ``(C)`` → ©
* ``(tm)``, ``(TM)`` → ™
* ``(r)``, ``(R)`` → ®
* ``+-`` → ±
* ``...`` → …
* ``?....`` → ?..
* ``!....`` → !..
* ``????????`` → ???
* ``!!!!!`` → !!!
* ``,,,`` → ,
* ``--`` → &ndash
* ``---`` → &mdash