Merge pull request #110 from eubinecto/issue_109

version 3.2.3 -

README.md

@@ -77,6 +77,60 @@ pprint(" ".join([styler(sent, 2) for sent in sents]))  # 2 = formal
  '횡하게 달아나는 겝니다.')
 ```
 
+### 4️⃣ `add_rules` of your own
+
+you can add your own rules with `add_rules` method:
+```python3
+styler.add_rules(
+    {"이🏷VCP🔗(?P<MASK>다🏷EF)": (
+        {"다🏷EF"},
+        {"에요🏷EF"},  # 에요.
+        {"습니다🏷EF"},
+    )
+    })
+sent = "한글은 한국의 글자이다."
+print(styler(sent, 1))
+```
+```text 
+한글은 한국의 글자에요.
+```
+You can add multiple rules altogether too. Use `politely.SELF` to refer to the original word.
+```python3
+from politely import SELF
+styler.add_rules(
+    {
+        r"(?P<MASK>(아빠|아버지|아버님)🏷NNG)": (
+            {f"아빠🏷NNG"},
+            {f"아버지🏷NNG", f"아버님🏷NNG"},
+            {f"아버지🏷NNG", f"아버님🏷NNG"}
+        ),
+        r"(아빠|아버지|아버님)🏷NNG🔗(?P<MASK>\S+?🏷JKS)": (
+            {SELF},  #  no change, replace with the original
+            {f"께서🏷JKS"},
+            {f"께서🏷JKS"}
+        ),
+        r"(?P<MASK>ᆫ다🏷EF)": (
+            {SELF},  # no change, replace with the original
+            {"시🏷EP🔗어요🏷EF"},
+            {"시🏷EP🔗습니다🏷EF"},
+        )
+    }
+)
+sent = "아빠가 정실에 들어간다."
+print(styler(sent, 1))
+from pprint import pprint
+pprint(styler.logs['guess']['out'])  # you can look up the candidates from here
+```
+```text
+아버지께서 정실에 들어가셔요.
+[(['아버지🏷NNG', '께서🏷JKS', '정실🏷NNG', '에🏷JKB', '들어가🏷VV', '시🏷EP', '어요🏷EF', '.🏷SF'],
+  0.0125),
+ (['아버님🏷NNG', '께서🏷JKS', '정실🏷NNG', '에🏷JKB', '들어가🏷VV', '시🏷EP', '어요🏷EF', '.🏷SF'],
+  0.0125)]
+```
+
+
+
 ## Hosting the interactive demo 
 
 You can either host the interactive demo locally ([you first have to sign up for papago API to get your secrets](https://developers.naver.com/docs/papago/README.md))

explore/add_rules_eg_1.py

@@ -0,0 +1,13 @@
+from politely import Styler
+styler = Styler()
+sent = "한글은 한국의 글자이다."
+styler.rules.clear()  # just for demonstration
+print(styler(sent, 1))  # should be wrong
+styler.add_rules(
+    {"이🏷VCP🔗(?P<MASK>다🏷EF)": (
+        {"다🏷EF"},
+        {"에요🏷EF"},  # 에요.
+        {"습니다🏷EF"},
+    )
+    })
+print(styler(sent, 1))  # should be this

explore/add_rules_eg_2.py

@@ -0,0 +1,27 @@
+from pprint import pprint
+
+from politely import SELF, Styler
+styler = Styler()
+styler.rules.clear()
+sent = "아빠가 정실에 들어간다."
+styler.add_rules(
+    {
+        r"(?P<MASK>(아빠|아버지|아버님)🏷NNG)": (
+            {f"아빠🏷NNG"},
+            {f"아버지🏷NNG", f"아버님🏷NNG"},
+            {f"아버지🏷NNG", f"아버님🏷NNG"}
+        ),
+        r"(아빠|아버지|아버님)🏷NNG🔗(?P<MASK>\S+?🏷JKS)": (
+            {SELF},
+            {f"께서🏷JKS"},
+            {f"께서🏷JKS"}
+        ),
+        r"(?P<MASK>ᆫ다🏷EF)": (
+            {SELF},
+            {"시🏷EP🔗어요🏷EF"},
+            {"시🏷EP🔗습니다🏷EF"},
+        )
+    }
+)
+print(styler(sent, 1))
+pprint(styler.logs['guess']['out'])

politely/__init__.py

@@ -1,4 +1,4 @@
-from politely.rules import SEP, TAG, NULL, MASK, SELF, RULES, PREFERENCES, CASUAL, POLITE, FORMAL  # noqa
+from politely.rules import SEP, TAG, NULL, SELF, RULES, PREFERENCES, CASUAL, POLITE, FORMAL  # noqa
 from politely.styler import Styler  # noqa
 
-__version__ = "v3.2.2"
+__version__ = "v3.2.3"

politely/errors.py

@@ -5,7 +5,7 @@
 
 class SFNotIncludedError(Exception):
     """
-    Exception raised when a sentence fragment is not included in the SF list.
+    An exception raised when a sentence does not include a SF.
     """
 
     def __init__(self, out: str):
@@ -15,7 +15,22 @@ def __str__(self) -> str:
         return "Sentence does not include a SF:\n" + "\n".join(self.out)
 
 
+class EFNotIncludedError(Exception):
+    """
+    An exception raised when a sentence does not include an EF.
+    """
+
+    def __init__(self, out: str):
+        self.out = out
+
+    def __str__(self) -> str:
+        return "Sentence does not include an EF:\n" + "\n".join(self.out)
+
+
 class EFNotSupportedError(Exception):
+    """
+    An exception raised when a sentence includes an EF that is not supported.
+    """
     def __init__(self, out: str):
         self.out = out
 

politely/fetchers.py

@@ -1,15 +1,4 @@
 from kiwipiepy import Kiwi
-from politely.scorer import Scorer
-
-
-def fetch_scorer() -> Scorer:
-    """
-    use fetch_scorer to
-    """
-    # as of right now, Scorer is not really "fetched".
-    # we define this function nevertheless, as  we will need this by the time
-    # we use n-grams for the scorer.
-    return Scorer()
 
 
 def fetch_kiwi() -> Kiwi:

politely/rules.py

@@ -4,13 +4,7 @@
 NULL = "❌"
 TAG = "🏷"
 SEP = "🔗"
-MASK = "MASK"
 
-# --- regex --- #
-ALL = rf"[^\s{SEP}{TAG}]"  # all characters except whitespace, sep and tag
-EFS = rf"(?P<{MASK}>{ALL}+?{TAG}EF)"
-SELF = rf"\g<{MASK}>"
-WITH_JS = rf"[{''.join({chr(i) for i in range(44032, 55204)} - {chr(44032 + 28 * i) for i in range(399)})}]"
 
 # --- all EF's of different styles --- #
 CASUAL = {
@@ -31,6 +25,7 @@
 
 POLITE = {
     f"어요{TAG}EF",
+    f"시{TAG}EP{SEP}어요{TAG}EF",
     f"에요{TAG}EF",
     f"죠{TAG}EF",
     f"래요{TAG}EF",
@@ -44,6 +39,7 @@
 
 FORMAL = {
     f"습니다{TAG}EF",
+    f"시{TAG}EP{SEP}습니다{TAG}EF",
     f"습니까{TAG}EF",
     f"ᆸ니까{TAG}EF",
     f"ᆸ시오{TAG}EF",
@@ -52,6 +48,12 @@
 }
 
 
+# --- regex --- #
+EFS = rf"(?P<MASK>({'|'.join([pair for pair in (CASUAL | POLITE | FORMAL)])}))"
+SELF = rf"\g<MASK>"
+WITH_JONG_SUNG = rf"[{''.join({chr(i) for i in range(44032, 55204)} - {chr(44032 + 28 * i) for i in range(399)})}]"
+
+
 # --- programmatically populated RULES --- #
 RULES: Dict[str, Tuple[Set[str], Set[str], Set[str]]] = dict()
 
@@ -64,19 +66,10 @@
     )
 })
 
-# --- 시/EP (1): 시/으시로 끝나지 않는 VV의 경우, 뒤에 시 or 으시가 필요할 수도 있다 --- #
-RULES.update({
-    rf"(?P<{MASK}>{ALL}+?{TAG}VV){SEP}(?!(시|으시){TAG}EP)": (
-        {SELF},
-        {SELF, rf"{SELF}{SEP}시{TAG}EP", rf"{SELF}{SEP}으시{TAG}EP"},  # we should be able to do back-referencing
-        {SELF, rf"{SELF}{SEP}시{TAG}EP", rf"{SELF}{SEP}으시{TAG}EP"}
-    )
-})
-
-# --- 시/EP (2): 이미 시/EP가 존재하는 경우, 반말을 쓸 때 제거한다 --- #
+# --- 시/EP: 이미 시/EP가 존재하는 경우, 반말을 쓸 때 제거한다 --- #
 RULES.update(
     {
-        rf"(?P<{MASK}>(시|으시){TAG}EP)": (
+        rf"(?P<MASK>(시|으시){TAG}EP)": (
             {NULL},  # you don't use them
             {SELF},  # just repeat yourself
             {SELF},  # just repeat yourself
@@ -88,7 +81,7 @@
 # --- 종성이 있는 경우, 종성으로 시작하는 EF는 사용하지 않음 --- #
 RULES.update(
     {
-        rf"{WITH_JS}{TAG}[A-Z\-]+?{SEP}{EFS}": (
+        rf"{WITH_JONG_SUNG}{TAG}[A-Z\-]+?{SEP}{EFS}": (
             CASUAL - {f"ᆫ다{TAG}EF", f"ᆯ게{TAG}EF", f"ᆫ대{TAG}EF"},
             POLITE - {f"ᆯ게요{TAG}EF", f"ᆫ대요{TAG}EF", f"ᆫ가요{TAG}EF"},
             FORMAL - {f"ᆸ니까{TAG}EF", f"ᆸ시오{TAG}EF", f"ᆸ니다{TAG}EF", f"ᆸ시다{TAG}EF"}
@@ -111,7 +104,7 @@
 # --- 나/저 --- #
 RULES.update(
     {
-        rf"(?P<{MASK}>(나|저){TAG}NP)": (
+        rf"(?P<MASK>(나|저){TAG}NP)": (
             {f"나{TAG}NP"},
             {f"저{TAG}NP"},
             {f"저{TAG}NP"}
@@ -123,7 +116,7 @@
 # --- 너/당신 --- #
 RULES.update(
     {
-        rf"(?P<{MASK}>(너|당신){TAG}NP)": (
+        rf"(?P<MASK>(너|당신){TAG}NP)": (
             {f"너{TAG}NP"},
             {f"당신{TAG}NP"},
             {f"당신{TAG}NP"}
@@ -135,10 +128,10 @@
 # --- 엄마/어머니 --- #
 RULES.update(  # noqa
     {
-        rf"(?P<{MASK}>(엄마|어머니){TAG}NNG)": (
+        rf"(?P<MASK>(엄마|어머니|어머님){TAG}NNG)": (
             {f"엄마{TAG}NNG"},
-            {f"어머니{TAG}NNG"},
-            {f"어머니{TAG}NNG"}
+            {f"어머니{TAG}NNG", f"어머님{TAG}NNG"},
+            {f"어머니{TAG}NNG", f"어머님{TAG}NNG"}
         )
     }
 )
@@ -147,18 +140,18 @@
 # --- 아빠/아버지 --- #
 RULES.update(
     {
-        rf"(?P<{MASK}>(아빠|아버지){TAG}NNG)": (
-            {f"아빠{TAG}NNG"},
+        rf"(?P<MASK>(아빠|아버지|아버님){TAG}NNG)": (
             {f"아빠{TAG}NNG"},
-            {f"아빠{TAG}NNG"}
+            {f"아버지{TAG}NNG", f"아버님{TAG}NNG"},
+            {f"아버지{TAG}NNG", f"아버님{TAG}NNG"}
         )
     }
 )
 
 # --- 께서 --- #
 RULES.update(
     {
-        rf"(엄마|어머니|아빠|아버지|선생님|할머니|할아버지){TAG}NNG{SEP}(?P<{MASK}>{SEP}{ALL}{TAG}JKS)": (
+        rf"(어머니|어머님|아버지|아버님|선생님|할머니|할아버지){TAG}NNG{SEP}(?P<MASK>\S+?{TAG}JKS)": (
             {SELF},
             {f"께서{TAG}JKS"},
             {f"께서{TAG}JKS"}