tdf#158454 Add Thai Autocorrect Support, coding part

SvxAutoCorrDoc::ChgAutoCorrWord() implementations: correct multiple patterns

* include/editeng/svxacorr.hxx, editeng/source/misc/svxacorr.cxx:
- Add classes SvxAutocorrWordList::{Iterator,WordSearchStatus}.
- Make SvxAutocorrWordList::SearchWordsInList() return WordSearchStatus
so the search can be continued with the added
SvxAutocorrWordList::SearchWordsNext() method.
- Make SvxAutoCorrect::SearchWordsInList(), and its lcl_SearchWordsInList()
companion, return WordSearchStatus propagated from
SvxAutocorrWordList::SearchWordsInList().
- SvxAutocorrWordList::WordMatches():
The existing mechanism of preventing collision of patterns like in
tdf#83037 (→ and ← and ↔ autocorrect collisions) was by storing
the matched string of wildcard pattern back to the list without
overwriting existing one. If the matched string was found in the list,
it would just be treated as no matching.
While this worked well for collision prevention, it caused failure
on the new exhaustive wildcard pattern visiting method when autocorrecting
the second text chunk with the same content. In such situation,
all intermediate stages of corrections of the first text chunk would be
recorded into the list. And, in the second chunk, the first stage would
just be applied from the recorded pattern, but all the next stages
would be refused due to the "collision" with the recorded patterns.
Moreover, the new method would cause the list to grow more quickly
as the autocorrections are done.
To solve the problem, just "peek" for the collision instead of
actually storing it. And SvxAutocorrWordList::ContainsPattern()
is added for this purpose.
* editeng/qa/unit/core-test.cxx:
- Modify TestAutoCorrDoc::ChgAutoCorrWord() to iterate through all patterns,
instead of finishing at the first one.
* editeng/source/editeng/edtspell.cxx:
- Ditto for EdtAutoCorrDoc::ChgAutoCorrWord().
* sw/source/core/edit/acorrect.cxx:
- Ditto for SwAutoCorrDoc::ChgAutoCorrWord().
- SwAutoCorrDoc::ChgAutoCorrWord(): Remove old dead code for autocorrection
on text with redlines.
* sw/qa/extras/uiwriter/uiwriter6.cxx,
+sw/qa/extras/uiwriter/data/tdf158454.odt:
- Add unit test "testTdf158454".

Change-Id: I8fb4a628a977b79b0ed2f239fd3749f15823b5df
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/160160
Tested-by: Jenkins
Reviewed-by: Jonathan Clark <jonathan@libreoffice.org>

1 files changed, 63 insertions, 9 deletions

diff --git a/include/editeng/svxacorr.hxx b/include/editeng/svxacorr.hxx
index d85a3d242783..d30a9795a743 100644
--- a/include/editeng/svxacorr.hxx
+++ b/include/editeng/svxacorr.hxx
@@ -163,15 +163,62 @@ class EDITENG_DLLPUBLIC SvxAutocorrWordList
     SvxAutocorrWordList( const SvxAutocorrWordList& ) = delete;
     const SvxAutocorrWordList& operator= ( const SvxAutocorrWordList& ) = delete;
 
-    const SvxAutocorrWord* WordMatches(const SvxAutocorrWord *pFnd,
-                                       std::u16string_view rTxt,
-                                       sal_Int32 &rStt,
-                                       sal_Int32 nEndPos) const;
+    std::optional<SvxAutocorrWord> WordMatches(const SvxAutocorrWord *pFnd,
+                                               std::u16string_view rTxt,
+                                               sal_Int32 &rStt,
+                                               sal_Int32 nEndPos) const;
 public:
+    class EDITENG_DLLPUBLIC Iterator {
+        struct Impl;
+        std::unique_ptr<Impl> mpImpl;
+
+        // For construction from containers in *SvxAutocorrWordList::mpImpl
+        friend class SvxAutocorrWordList;
+        Iterator(std::unique_ptr<Impl> pImpl);
+
+    public:
+        Iterator(const Iterator& it);
+        ~Iterator();
+        bool Step();
+        const SvxAutocorrWord& operator*() const;
+        const SvxAutocorrWord* operator->() const;
+    };
+
+    class EDITENG_DLLPUBLIC WordSearchStatus {
+        SvxAutocorrWord               mFnd;
+
+        // For iteration
+        friend class SvxAutocorrWordList;
+        const SvxAutocorrWordList*    mpAutocorrWordList;
+        SvxAutocorrWordList::Iterator mAutocorrWordListIter;
+
+    public:
+        WordSearchStatus(
+            const SvxAutocorrWord& aFnd,
+            const SvxAutocorrWordList* pAutocorrWordList,
+            const SvxAutocorrWordList::Iterator& autocorrWordListIter
+        ) : mFnd(aFnd), mpAutocorrWordList(pAutocorrWordList),
+            mAutocorrWordListIter(autocorrWordListIter)
+        {}
+        const SvxAutocorrWord* GetAutocorrWord() const {
+            return &mFnd;
+        }
+        const SvxAutocorrWordList* GetAutocorrWordList() const {
+            return mpAutocorrWordList;
+        }
+        const SvxAutocorrWord* GetWordAtIter() const {
+            return &*mAutocorrWordListIter;
+        }
+        bool StepIter() {
+            return mAutocorrWordListIter.Step();
+        }
+    };
+
     SvxAutocorrWordList();
                            // free any objects still in the set
                            ~SvxAutocorrWordList();
     void                   DeleteAndDestroyAll();
+    bool                   ContainsPattern(const OUString& sShort) const;
     const SvxAutocorrWord* Insert(SvxAutocorrWord aWord) const;
     std::optional<SvxAutocorrWord> FindAndRemove(const SvxAutocorrWord *pWord);
     void                   LoadEntry(const OUString& sWrong, const OUString& sRight, bool bOnlyTxt);
@@ -181,7 +228,10 @@ public:
     typedef std::vector<SvxAutocorrWord> AutocorrWordSetType;
     const AutocorrWordSetType & getSortedContent() const;
 
-    const SvxAutocorrWord* SearchWordsInList(std::u16string_view rTxt, sal_Int32& rStt, sal_Int32 nEndPos) const;
+    std::optional<WordSearchStatus>
+    SearchWordsInList(std::u16string_view rTxt, sal_Int32& rStt, sal_Int32 nEndPos) const;
+    bool
+    SearchWordsNext(std::u16string_view rTxt, sal_Int32& rStt, sal_Int32 nEndPos, WordSearchStatus& rStatus) const;
 };
 
 class EDITENG_DLLPUBLIC SvxAutoCorrectLanguageLists
@@ -323,10 +373,14 @@ public:
     // nEnd - to check position - as of this item forward
     // rLang - Input: in which language is searched
     //         Output: in which "language list" was it found
-    const SvxAutocorrWord* SearchWordsInList( std::u16string_view rTxt,
-                                    sal_Int32& rStt, sal_Int32 nEndPos,
-                                    SvxAutoCorrDoc& rDoc,
-                                    LanguageTag& rLang );
+    std::optional<SvxAutocorrWordList::WordSearchStatus>
+    SearchWordsInList( std::u16string_view rTxt,
+                       sal_Int32& rStt, sal_Int32 nEndPos,
+                       SvxAutoCorrDoc& rDoc,
+                       LanguageTag& rLang );
+    static bool SearchWordsNext( std::u16string_view rTxt,
+                          sal_Int32& rStt, sal_Int32 nEndPos,
+                          SvxAutocorrWordList::WordSearchStatus& rStatus );
 
     // Query/Set the Character for the Quote substitution
     sal_Unicode GetStartSingleQuote() const         { return cStartSQuote; }