Commit 21f1b393 for tesseract
commit 21f1b39358929a7b20b47ef39b806dc81aa3b2b4
Author: Viktor Szépe <viktor@szepe.net>
Date: Thu Jan 1 16:59:05 2026 +0100
Fix typos (#4497)
diff --git a/src/api/baseapi.cpp b/src/api/baseapi.cpp
index 37020fa9..3b31b65a 100644
--- a/src/api/baseapi.cpp
+++ b/src/api/baseapi.cpp
@@ -1041,7 +1041,7 @@ bool TessBaseAPI::ProcessPagesInternal(const char *filename, const char *retry_c
tesseract_->tessedit_page_number);
}
- // At this point we are officially in autodection territory.
+ // At this point we are officially in autodetection territory.
// That means any data in stdin must be buffered, to make it
// seekable.
std::string buf;
diff --git a/src/api/pagerenderer.cpp b/src/api/pagerenderer.cpp
index cd2d0a5e..2ae64d32 100644
--- a/src/api/pagerenderer.cpp
+++ b/src/api/pagerenderer.cpp
@@ -473,7 +473,7 @@ Pta *ClipAndSimplifyBaseline(Pta *bottom_pts, Pta *baseline_pts,
}
///
-/// Fit the baseline points into the existings polygon
+/// Fit the baseline points into the existing polygon
///
Pta *FitBaselineIntoLinePolygon(Pta *bottom_pts, Pta *baseline_pts,
tesseract::WritingDirection writing_direction) {
diff --git a/src/ccmain/equationdetect.cpp b/src/ccmain/equationdetect.cpp
index 7e4bbe6d..6cfa5dcf 100644
--- a/src/ccmain/equationdetect.cpp
+++ b/src/ccmain/equationdetect.cpp
@@ -48,7 +48,7 @@ static BOOL_VAR(equationdetect_save_seed_image, false, "Save the seed image");
static BOOL_VAR(equationdetect_save_merged_image, false, "Save the merged image");
///////////////////////////////////////////////////////////////////////////
-// Utility ColParition sort functions.
+// Utility ColPartition sort functions.
///////////////////////////////////////////////////////////////////////////
static int SortCPByTopReverse(const void *p1, const void *p2) {
const ColPartition *cp1 = *static_cast<ColPartition *const *>(p1);
@@ -599,7 +599,7 @@ float EquationDetect::ComputeForegroundDensity(const TBOX &tbox) {
bool EquationDetect::CheckSeedFgDensity(const float density_th, ColPartition *part) {
ASSERT_HOST(part);
- // Split part horizontall, and check for each sub part.
+ // Split part horizontally, and check for each sub part.
std::vector<TBOX> sub_boxes;
SplitCPHorLite(part, &sub_boxes);
float parts_passed = 0.0;
@@ -1438,7 +1438,7 @@ void EquationDetect::PrintSpecialBlobsDensity(const ColPartition *part) const {
ASSERT_HOST(part);
TBOX box(part->bounding_box());
int h = pixGetHeight(lang_tesseract_->BestPix());
- tprintf("Printing special blobs density values for ColParition (t=%d,b=%d) ", h - box.top(),
+ tprintf("Printing special blobs density values for ColPartition (t=%d,b=%d) ", h - box.top(),
h - box.bottom());
box.print();
tprintf("blobs count = %d, density = ", part->boxes_count());
diff --git a/src/ccstruct/coutln.cpp b/src/ccstruct/coutln.cpp
index db2e1cd6..55221d13 100644
--- a/src/ccstruct/coutln.cpp
+++ b/src/ccstruct/coutln.cpp
@@ -577,7 +577,7 @@ int16_t C_OUTLINE::turn_direction() const { // winding number
* Reverse the direction of an outline.
*/
-void C_OUTLINE::reverse() { // reverse drection
+void C_OUTLINE::reverse() { // reverse direction
DIR128 halfturn = MODULUS / 2; // amount to shift
DIR128 stepdir; // direction of step
int16_t stepindex; // index to cstep
diff --git a/src/ccstruct/matrix.h b/src/ccstruct/matrix.h
index a97912ad..7fa344e7 100644
--- a/src/ccstruct/matrix.h
+++ b/src/ccstruct/matrix.h
@@ -146,7 +146,7 @@ public:
}
// Writes to the given file. Returns false in case of error.
- // Only works with bitwise-serializeable types!
+ // Only works with bitwise-serializable types!
bool Serialize(FILE *fp) const {
if (!SerializeSize(fp)) {
return false;
@@ -170,7 +170,7 @@ public:
}
// Reads from the given file. Returns false in case of error.
- // Only works with bitwise-serializeable types!
+ // Only works with bitwise-serializable types!
// If swap is true, assumes a big/little-endian swap is needed.
bool DeSerialize(bool swap, FILE *fp) {
if (!DeSerializeSize(swap, fp)) {
diff --git a/src/ccstruct/ratngs.cpp b/src/ccstruct/ratngs.cpp
index 66d032bd..502ec4f4 100644
--- a/src/ccstruct/ratngs.cpp
+++ b/src/ccstruct/ratngs.cpp
@@ -660,7 +660,7 @@ int WERD_CHOICE::GetTopScriptID() const {
return max_sid;
}
-// Fixes the state_ for a chop at the given blob_posiiton.
+// Fixes the state_ for a chop at the given blob_position.
void WERD_CHOICE::UpdateStateForSplit(int blob_position) {
int total_chunks = 0;
for (unsigned i = 0; i < length_; ++i) {
diff --git a/src/ccstruct/ratngs.h b/src/ccstruct/ratngs.h
index e9371c9c..cf18a95e 100644
--- a/src/ccstruct/ratngs.h
+++ b/src/ccstruct/ratngs.h
@@ -552,7 +552,7 @@ public:
// Note that for Japanese, Hiragana and Katakana are simply treated as Han.
int GetTopScriptID() const;
- // Fixes the state_ for a chop at the given blob_posiiton.
+ // Fixes the state_ for a chop at the given blob_position.
void UpdateStateForSplit(int blob_position);
// Returns the sum of all the state elements, being the total number of blobs.
@@ -569,7 +569,7 @@ public:
// one displayed) and waits for a click in the window.
void DisplaySegmentation(TWERD *word);
- WERD_CHOICE &operator+=( // concatanate
+ WERD_CHOICE &operator+=( // concatenate
const WERD_CHOICE &second); // second on first
WERD_CHOICE &operator=(const WERD_CHOICE &source);
diff --git a/src/ccstruct/rejctmap.h b/src/ccstruct/rejctmap.h
index beeb5373..fc4b9780 100644
--- a/src/ccstruct/rejctmap.h
+++ b/src/ccstruct/rejctmap.h
@@ -75,7 +75,7 @@ enum REJ_FLAGS {
/* Reject modes generated after MM_ACCEPT but before QUALITY_ACCEPT */
R_BAD_QUALITY, // TEMP Quality metrics bad for WERD
- /* Reject modes generated after QUALITY_ACCEPT but before MINIMAL_REJ accep*/
+ /* Reject modes generated after QUALITY_ACCEPT but before MINIMAL_REJ accept */
R_DOC_REJ, // TEMP Document rejection
R_BLOCK_REJ, // TEMP Block rejection
R_ROW_REJ, // TEMP Row rejection
diff --git a/src/ccstruct/werd.cpp b/src/ccstruct/werd.cpp
index 36aa0b60..287c82f2 100644
--- a/src/ccstruct/werd.cpp
+++ b/src/ccstruct/werd.cpp
@@ -513,7 +513,7 @@ void WERD::GetNoiseOutlines(std::vector<C_OUTLINE *> *outlines) {
}
}
-// Adds the selected outlines to the indcated real blobs, and puts the rest
+// Adds the selected outlines to the indicated real blobs, and puts the rest
// back in rej_cblobs where they came from. Where the target_blobs entry is
// nullptr, a run of wanted outlines is put into a single new blob.
// Ownership of the outlines is transferred back to the word. (Hence
diff --git a/src/ccstruct/werd.h b/src/ccstruct/werd.h
index 2c19ef1e..6e5b405a 100644
--- a/src/ccstruct/werd.h
+++ b/src/ccstruct/werd.h
@@ -174,7 +174,7 @@ public:
// Extracts all the noise outlines and stuffs the pointers into the given
// vector of outlines. Afterwards, the outlines vector owns the pointers.
void GetNoiseOutlines(std::vector<C_OUTLINE *> *outlines);
- // Adds the selected outlines to the indcated real blobs, and puts the rest
+ // Adds the selected outlines to the indicated real blobs, and puts the rest
// back in rej_cblobs where they came from. Where the target_blobs entry is
// nullptr, a run of wanted outlines is put into a single new blob.
// Ownership of the outlines is transferred back to the word. (Hence
diff --git a/src/ccutil/unicharset.h b/src/ccutil/unicharset.h
index dd0ff8f3..a37ad5cf 100644
--- a/src/ccutil/unicharset.h
+++ b/src/ccutil/unicharset.h
@@ -569,7 +569,7 @@ public:
// src_unicharset with ranges in it. The unicharsets don't have to be the
// same, and graphemes are correctly accounted for.
void ExpandRangesFromOther(const UNICHARSET &src);
- // Makes this a copy of src. Clears this completely first, so the automattic
+ // Makes this a copy of src. Clears this completely first, so the automatic
// ids will not be present in this if not in src.
void CopyFrom(const UNICHARSET &src);
// For each id in src, if it does not occur in this, add it, as in
diff --git a/src/classify/intmatcher.h b/src/classify/intmatcher.h
index d46100cb..167e87a5 100644
--- a/src/classify/intmatcher.h
+++ b/src/classify/intmatcher.h
@@ -22,7 +22,7 @@
namespace tesseract {
-// Character fragments could be present in the trained templaes
+// Character fragments could be present in the trained templates
// but turned on/off on the language-by-language basis or depending
// on particular properties of the corpus (e.g. when we expect the
// images to have low exposure).
diff --git a/src/dict/dict.h b/src/dict/dict.h
index 3290dd0b..51872bcc 100644
--- a/src/dict/dict.h
+++ b/src/dict/dict.h
@@ -280,7 +280,7 @@ public:
/* dict.cpp ****************************************************************/
/// Initialize Dict class - load dawgs from [lang].traineddata and
- /// user-specified wordlist and parttern list.
+ /// user-specified wordlist and pattern list.
static DawgCache *GlobalDawgCache();
// Sets up ready for a Load or LoadLSTM.
void SetupForLoad(DawgCache *dawg_cache);
@@ -423,7 +423,7 @@ public:
/// For each of the character classes of the given unichar_id (and the
/// unichar_id itself) finds the corresponding outgoing node or self-loop
/// in the given dawg and (after checking that it is valid) records it in
- /// dawg_args->updated_ative_dawgs. Updates current_permuter if any valid
+ /// dawg_args->updated_active_dawgs. Updates current_permuter if any valid
/// edges were found.
void ProcessPatternEdges(const Dawg *dawg, const DawgPosition &info, UNICHAR_ID unichar_id,
bool word_end, DawgArgs *dawg_args,
diff --git a/src/textord/edgloop.cpp b/src/textord/edgloop.cpp
index 87dab705..bbee5618 100644
--- a/src/textord/edgloop.cpp
+++ b/src/textord/edgloop.cpp
@@ -127,7 +127,7 @@ int16_t loop_bounding_box( // get bounding box
realstart = start;
botleft = topright = ICOORD(edgept->pos.x(), edgept->pos.y());
leftmost = edgept->pos.x();
- length = 0; // coutn length
+ length = 0; // count length
do {
edgept = edgept->next;
if (edgept->pos.x() < botleft.x()) {
diff --git a/src/textord/makerow.cpp b/src/textord/makerow.cpp
index 3d89b711..ca7aea7b 100644
--- a/src/textord/makerow.cpp
+++ b/src/textord/makerow.cpp
@@ -2078,7 +2078,7 @@ void make_baseline_spline(TO_ROW *row, // row to fit
bool segment_baseline( // split baseline
TO_ROW *row, // row to fit
TO_BLOCK *block, // block it came from
- int32_t &segments, // no fo segments
+ int32_t &segments, // no of segments
int32_t *xstarts // coords of segments
) {
bool needs_curve; // needs curved line
@@ -2175,7 +2175,7 @@ bool segment_baseline( // split baseline
double *linear_spline_baseline( // split baseline
TO_ROW *row, // row to fit
TO_BLOCK *block, // block it came from
- int32_t &segments, // no fo segments
+ int32_t &segments, // no of segments
int32_t xstarts[] // coords of segments
) {
int blobcount; // no of blobs
diff --git a/src/textord/makerow.h b/src/textord/makerow.h
index cfee8ec6..3987d3f8 100644
--- a/src/textord/makerow.h
+++ b/src/textord/makerow.h
@@ -217,13 +217,13 @@ void make_baseline_spline(TO_ROW *row, // row to fit
bool segment_baseline( // split baseline
TO_ROW *row, // row to fit
TO_BLOCK *block, // block it came from
- int32_t &segments, // no fo segments
+ int32_t &segments, // no of segments
int32_t *xstarts // coords of segments
);
double *linear_spline_baseline( // split baseline
TO_ROW *row, // row to fit
TO_BLOCK *block, // block it came from
- int32_t &segments, // no fo segments
+ int32_t &segments, // no of segments
int32_t xstarts[] // coords of segments
);
void assign_blobs_to_rows( // find lines
diff --git a/src/textord/pitsync1.cpp b/src/textord/pitsync1.cpp
index 5de3b768..7999558e 100644
--- a/src/textord/pitsync1.cpp
+++ b/src/textord/pitsync1.cpp
@@ -91,7 +91,7 @@ FPSEGPT::FPSEGPT( // constructor
double mean; // mean pitch
double total; // total dists
double factor; // cost function
- FPSEGPT_IT pred_it = prev_list; // for previuos segment
+ FPSEGPT_IT pred_it = prev_list; // for previous segment
cost = FLT_MAX;
pred = nullptr;
diff --git a/src/textord/tabfind.cpp b/src/textord/tabfind.cpp
index fb6d99ae..45d47e72 100644
--- a/src/textord/tabfind.cpp
+++ b/src/textord/tabfind.cpp
@@ -133,7 +133,7 @@ void TabFind::SetBlockRuleEdges(TO_BLOCK *block) {
}
// Sets the left and right rule and crossing_rules for the blobs in the given
-// list by fiding the next outermost tabvectors for each blob.
+// list by finding the next outermost tabvectors for each blob.
void TabFind::SetBlobRuleEdges(BLOBNBOX_LIST *blobs) {
BLOBNBOX_IT blob_it(blobs);
for (blob_it.mark_cycle_pt(); !blob_it.cycled_list(); blob_it.forward()) {